© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16823
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and social interactions

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

    acting on

    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
    Jeografia
    -0.68
    pecabe
    -0.60
    ConstraintMaker
    -0.53
     guys
    -0.51
     anún
    -0.49
    protetor
    -0.49
     yells
    -0.47
    非常的
    -0.47
    ualaikum
    -0.47
     FUCK
    -0.46
    POSITIVE LOGITS
     serupa
    0.51
     freilich
    0.45
     mengenakan
    0.44
    ruptedException
    0.44
    yarnpkg
    0.42
     davantage
    0.42
     столь
    0.41
     InputDecoration
    0.40
     setMessage
    0.40
     (!_
    0.40
    Activations Density 0.118%

    No Known Activations