Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1729
    Prev
    Next
    INDEX
    Explanations

    mentions of the AV (audio-visual) format and related technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextInputType
    -0.83
     Rahman
    -0.77
     Lightroom
    -0.75
     matter
    -0.74
     Christy
    -0.74
     GSH
    -0.74
     rootReducer
    -0.71
    Reino
    -0.71
    ieza
    -0.71
     peine
    -0.70
    POSITIVE LOGITS
    av
    1.45
     AV
    1.30
    AV
    1.27
     Av
    1.23
     av
    1.19
    Av
    1.14
     Aven
    1.06
     Avic
    1.04
    avro
    1.03
     Avenue
    1.02
    Activations Density 0.042%

    No Known Activations