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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 861
    Prev
    Next
    INDEX
    Explanations

    specific sequences or identifiers related to code or digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    interopRequire
    -0.70
    Portail
    -0.68
    cyklopedia
    -0.66
     pinulongan
    -0.65
    extAlignment
    -0.64
    ########.
    -0.63
     Roskov
    -0.63
    исленность
    -0.60
    protoimpl
    -0.59
     >=",
    -0.59
    POSITIVE LOGITS
    dafx
    0.47
    mande
    0.44
    ivir
    0.44
    初中
    0.42
    łop
    0.42
    TEP
    0.41
    {}/
    0.41
    krieg
    0.40
     чел
    0.40
     clip
    0.40
    Activations Density 0.269%

    No Known Activations