© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10102
    Prev
    Next
    INDEX
    Explanations

    concepts related to temperature and minimum/maximum values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms related to temperature measurement and control systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    abstract, polysyllabic nouns and formal terms (often Latinate), including their CamelCase components in code identifiers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "temperature" in programming code, particularly in contexts involving temperature-related variables and measurements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aussie
    -0.69
     pauv
    -0.66
     Inorg
    -0.66
    newVal
    -0.64
     Aussie
    -0.63
     insiders
    -0.60
    Rookie
    -0.59
     cools
    -0.59
    Indie
    -0.59
     comfy
    -0.59
    POSITIVE LOGITS
    }());
    0.66
     photograph
    0.55
     automobile
    0.54
    cplusplus
    0.53
     Photograph
    0.52
     telephone
    0.50
    ECONDS
    0.50
     examination
    0.49
     photographie
    0.48
     setDescription
    0.48
    Activations Density 0.506%

    No Known Activations