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. 12-GEMMASCOPE-RES-16K
    6. 12140
    Prev
    Next
    INDEX
    Explanations

    discussions about films and their impact, focusing on viewer responses and the creative process behind them

    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
    <eos>
    -0.78
     bağlantılar
    -0.59
    shank
    -0.53
    Durée
    -0.52
    CppMethod
    -0.50
    ","#
    -0.49
    ","");
    -0.48
    Rè
    -0.48
    errHandler
    -0.48
    twimg
    -0.47
    POSITIVE LOGITS
    </b>
    0.83
     resourceCulture
    0.79
    ?}
    0.72
     <<<<<<<<<<<<<<
    0.71
    новниш
    0.71
    …?
    0.68
    XmlAccessType
    0.68
    %?
    0.66
    ?
    0.66
    AddTagHelper
    0.65
    Activations Density 0.321%

    No Known Activations