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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27833
    Prev
    Next
    INDEX
    Explanations

    terms related to genre classifications, particularly in media or literature

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

    genre and genera

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diwedd
    -0.69
    makeConstraints
    -0.69
    навли
    -0.68
    RenderAtEndOf
    -0.68
    orianCalendar
    -0.65
    BindView
    -0.64
     nicio
    -0.59
     tenuta
    -0.59
     Redist
    -0.58
     Present
    -0.57
    POSITIVE LOGITS
     genres
    1.30
     Genre
    1.26
     genre
    1.25
    genre
    1.18
    Genre
    1.16
     Genres
    1.12
    genres
    1.03
    Genres
    1.02
    textTheme
    0.86
    gdx
    0.82
    Activations Density 0.010%

    No Known Activations