© 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. 16-GEMMASCOPE-RES-16K
    6. 8808
    Prev
    Next
    INDEX
    Explanations

    function definitions and function calls in code

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

    Lists or arrays manipulation

    np_acts-logits-general · gemini-2.0-flash

    list or array literal

    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
     osoba
    -0.48
    isen
    -0.44
    zji
    -0.44
    msk
    -0.43
     person
    -0.42
    ger
    -0.40
    ژی
    -0.40
     ujarnya
    -0.39
    site
    -0.39
    createServer
    -0.39
    POSITIVE LOGITS
    IsMutable
    0.97
    NSMutableArray
    0.89
    NSArray
    0.88
     list
    0.86
     comprised
    0.86
     lista
    0.83
     lijst
    0.81
     ARRAY
    0.80
     listOf
    0.79
    Datuak
    0.78
    Activations Density 0.433%

    No Known Activations