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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 10520
    Prev
    Next
    INDEX
    Explanations

    syntactical structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.77
    хьтан
    -0.67
    <bos>
    -0.65
    RegressionTest
    -0.63
    RTLD
    -0.63
    GEBURTSDATUM
    -0.61
     Roskov
    -0.61
    setVerticalGroup
    -0.59
     JpaRepository
    -0.58
     resourceCulture
    -0.55
    POSITIVE LOGITS
     doubtnut
    0.69
     stiefel
    0.61
    asjonen
    0.60
    cookieParser
    0.60
    omiast
    0.59
     ")");
    0.58
    owanym
    0.57
    ֏
    0.57
     (\<
    0.57
     ARXIV
    0.56
    Activations Density 1.307%

    No Known Activations