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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13270
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and clinical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mechan
    -0.39
    mek
    -0.38
     OFFIC
    -0.37
    mechan
    -0.37
     MECHAN
    -0.37
     Defenders
    -0.36
    ponen
    -0.36
    Re
    -0.35
    Ber
    -0.35
    hile
    -0.34
    POSITIVE LOGITS
     demografica
    0.65
    webElementXpaths
    0.55
     MaterialApp
    0.53
    Autoritní
    0.52
     tartalomajánló
    0.52
     समीक्षाएं
    0.51
    parsedMessage
    0.50
    ftagPool
    0.50
     newOwner
    0.50
     auroit
    0.48
    Activations Density 0.877%

    No Known Activations