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. 14-GEMMASCOPE-RES-16K
    6. 4528
    Prev
    Next
    INDEX
    Explanations

    code structures and performance-related keywords in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Knie
    -0.48
    sibly
    -0.47
     ICD
    -0.45
     ajud
    -0.44
    alité
    -0.43
    ,:);
    -0.43
     Charg
    -0.43
    views
    -0.42
     leu
    -0.42
    ścic
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.90
     resourceCulture
    0.79
    IntoConstraints
    0.77
    ChildScrollView
    0.71
    RetentionPolicy
    0.69
    EDEFAULT
    0.69
    oplayer
    0.67
    elemField
    0.65
    modelBuilder
    0.63
     comparative
    0.63
    Activations Density 0.174%

    No Known Activations