© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1791
    Prev
    Next
    INDEX
    Explanations

    code-related structures, especially those involving data serialization and layout constraints 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 @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.71
     aidant
    -0.60
     متعلقه
    -0.57
     nonatomic
    -0.55
    oredCriteria
    -0.55
    createStatement
    -0.55
    tagHelperRunner
    -0.54
    IVEREF
    -0.53
     bottlen
    -0.53
    ніципа
    -0.52
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.69
    getColumnIndex
    0.63
     jadx
    0.51
    DataAnnotations
    0.51
    BagConstraints
    0.51
     listas
    0.48
     hikariConfig
    0.48
    værende
    0.47
    سیون
    0.47
    ībā
    0.46
    Activations Density 0.172%

    No Known Activations