© 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. 3-GEMMASCOPE-RES-16K
    11. 16052
    Prev
    Next
    INDEX
    Explanations

    code-related concepts, specifically focusing on classes, methods, and attributes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.68
    UnusedPrivate
    -0.68
    SequentialGroup
    -0.67
    setVerticalGroup
    -0.65
    IsMutable
    -0.65
    ChildScrollView
    -0.63
    contentLoaded
    -0.63
    XMLSchema
    -0.62
    endphp
    -0.62
    AlterField
    -0.60
    POSITIVE LOGITS
    ethene
    0.64
     étrangère
    0.59
     democrática
    0.56
     antidote
    0.55
    liculas
    0.55
     phenotypes
    0.55
     submarines
    0.55
     capitals
    0.54
     authoritative
    0.54
     eletrônico
    0.54
    Activations Density 0.526%

    No Known Activations