© 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. 31-GEMMASCOPE-RES-16K
    6. 2070
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate explanations and clarifications in scientific contexts

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

    phrases that provide explanations or reasoning, often using words like "could", "would", "explain", or "helps explain".

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

    explanatory phrases that provide reasoning or justification for claims.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.54
    IsContent
    -0.54
     onPostExecute
    -0.50
    Personensuche
    -0.48
     فريبيس
    -0.48
    AnchorStyles
    -0.45
    Filmografie
    -0.44
    ütü
    -0.44
    hyrchwyd
    -0.44
    webElementGuid
    -0.44
    POSITIVE LOGITS
     explanation
    3.11
     explain
    2.86
     explanations
    2.84
     explaining
    2.67
     explained
    2.66
     Explanation
    2.56
     explains
    2.55
    explanation
    2.47
     explicación
    2.42
     explica
    2.41
    Activations Density 0.966%

    No Known Activations