© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21935
    Prev
    Next
    INDEX
    Explanations

    questions related to processes or implications

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

    asking what and how

    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
    Ƚ
    -0.48
    Попис
    -0.47
     sarili
    -0.42
    ſelves
    -0.42
    AISSEE
    -0.40
    ↹
    -0.39
     jednak
    -0.39
    ఔ
    -0.39
    lenz
    -0.39
    ſelf
    -0.39
    POSITIVE LOGITS
     consequently
    0.93
     therefore
    0.89
     subsequently
    0.86
    sequently
    0.79
    therefore
    0.78
    それに
    0.77
     consequent
    0.77
     dermed
    0.77
     thereby
    0.75
     consiguiente
    0.75
    Activations Density 0.020%

    No Known Activations