© 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. 8-GEMMASCOPE-RES-16K
    11. 2356
    Prev
    Next
    INDEX
    Explanations

    elements and structures used in programming or code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.92
    UrlResolution
    -0.87
    GIVEREF
    -0.81
    antMatchers
    -0.78
    copg
    -0.78
    ValueStyle
    -0.76
    DataAnnotations
    -0.71
    astify
    -0.69
    SharedDtor
    -0.67
     AssemblyCulture
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.72
    ↵
    0.60
    <eos>
    0.59
    ⤹
    0.53
    expandindo
    0.50
     própria
    0.49
    sätzlich
    0.48
     publiques
    0.48
    tvguidetime
    0.46
    ↵↵↵↵
    0.46
    Activations Density 0.078%

    No Known Activations