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 - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6819
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts particularly in programming and mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.77
    Билгалдахарш
    -0.70
     fair
    -0.67
     referrerpolicy
    -0.67
     BorderSide
    -0.66
     Tiong
    -0.65
    存于互联网档案馆
    -0.64
    sonder
    -0.63
    fair
    -0.63
    xla
    -0.63
    POSITIVE LOGITS
     peel
    0.59
     Browne
    0.58
    Mora
    0.57
    jooq
    0.56
     Priest
    0.55
    Kum
    0.54
     Pellegrini
    0.54
    AppMethodBeat
    0.53
    +:+
    0.53
     viss
    0.53
    Activations Density 3.229%

    No Known Activations