© 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. 15-GEMMASCOPE-RES-16K
    6. 2978
    Prev
    Next
    INDEX
    Explanations

    code snippets that involve array operations and function definitions

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

    syntactical structures involving variable assignments and function definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الو
    -0.41
     Rück
    -0.41
    ╰
    -0.41
     Z
    -0.40
     zurück
    -0.39
     toàn
    -0.39
    pr
    -0.38
     geri
    -0.38
    ام
    -0.38
     גל
    -0.38
    POSITIVE LOGITS
     للاسماء
    0.91
    Билгалдахарш
    0.76
     الحره
    0.75
    ^(@)
    0.75
    AnchorStyles
    0.75
    localctx
    0.75
    Източници
    0.74
    :+:
    0.72
    UnsafeEnabled
    0.70
    NOPQRST
    0.70
    Activations Density 0.100%

    No Known Activations