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. 16-GEMMASCOPE-RES-16K
    6. 1438
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and structures within programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Programming code and related symbols

    np_acts-logits-general · gemini-2.0-flash

    nullability and optional values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.54
    __*/
    -0.54
    >*/
    -0.51
    Portale
    -0.49
    抱
    -0.48
    BAST
    -0.47
     Wikispecies
    -0.46
     الحره
    -0.46
     статистики
    -0.46
     للمعارف
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.94
     null
    0.85
    Nullable
    0.82
     GenerationType
    0.79
    EDEFAULT
    0.74
     možná
    0.74
     nullptr
    0.70
    assertNull
    0.69
    ?.
    0.69
    ?
    0.69
    Activations Density 0.399%

    No Known Activations