© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10687
    Prev
    Next
    INDEX
    Explanations

    function calls in code snippets

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

    Code snippets with brackets/parentheses

    np_acts-logits-general · gemini-2.0-flash

    HIV prevention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scriptcase
    -0.67
    ment
    -0.60
    VARS
    -0.60
    ity
    -0.58
    }");
    -0.56
     wall
    -0.56
    kannya
    -0.54
     trị
    -0.54
    naeus
    -0.53
    AppCompatTheme
    -0.53
    POSITIVE LOGITS
    RetentionPolicy
    0.87
    GEBURTSDATUM
    0.83
     للمعارف
    0.79
    ScopeManager
    0.72
    queryInterface
    0.72
    wahati
    0.71
    SequentialGroup
    0.71
     MonoBehaviour
    0.70
     AssemblyCulture
    0.69
     calldata
    0.69
    Activations Density 0.083%

    No Known Activations