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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105894
    Prev
    Next
    INDEX
    Explanations

    instances of specific technical terms and instructions related to functionality and control

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

    overhang, grasp, injunction, supervision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <bos>
    -1.55
    enskap
    -0.73
    ítmény
    -0.71
    𝓴
    -0.63
    𝓲
    -0.62
    𝓫
    -0.61
    𝓸
    -0.60
    𝓵
    -0.59
    𝓭
    -0.59
    isa
    -0.58
    POSITIVE LOGITS
    s
    1.05
    ים
    0.71
    ième
    0.70
     sánchez
    0.66
    sweise
    0.63
     parís
    0.63
     rodríguez
    0.60
    stanbul
    0.59
     dezelve
    0.59
     saveiro
    0.59
    Activations Density 0.154%

    No Known Activations