© 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. 11022
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemical properties and activities of substances

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

    specialized scientific terminology and Latin names, particularly those related to biology and chemistry.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ainfi
    -0.91
     anún
    -0.90
     propOrder
    -0.83
    pecabe
    -0.79
    berdayakan
    -0.77
    alakip
    -0.75
    pantalón
    -0.74
    ientras
    -0.74
    ambién
    -0.73
    arangay
    -0.73
    POSITIVE LOGITS
    Leary
    0.61
    躇
    0.54
    ers
    0.52
    ment
    0.51
    AxisAlignment
    0.47
    zzleHttp
    0.46
    al
    0.46
    or
    0.46
    izer
    0.45
    asanjo
    0.45
    Activations Density 3.333%

    No Known Activations