Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24461
    Prev
    Next
    INDEX
    Explanations

    casual language and social interactions

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

    I wanna resource user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Whilst
    -0.36
    Whilst
    -0.36
     whilst
    -0.35
     endeavours
    -0.31
     אשר
    -0.31
    十分的
    -0.29
    }`
    -0.28
     poichè
    -0.28
    ::{
    -0.28
     referenties
    -0.28
    POSITIVE LOGITS
     dunno
    0.82
    addContainerGap
    0.75
     mijne
    0.72
     useless
    0.67
    verifyException
    0.66
     purpoſe
    0.66
     naviguant
    0.66
    ambién
    0.65
    useless
    0.65
     anyhow
    0.65
    Activations Density 0.030%

    No Known Activations