© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27670
    Prev
    Next
    INDEX
    Explanations

    PHP variable declarations and conditional statements

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

    `(` followed by code entities

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     }}$}
    -0.91
     CanadaChoose
    -0.88
    exitRule
    -0.86
    ///</
    -0.85
    \{\\
    -0.85
     Meksiku
    -0.84
    bewerken
    -0.83
    \}\\
    -0.82
     }}(
    -0.80
    </caption>
    -0.80
    POSITIVE LOGITS
    ing
    0.57
    zków
    0.55
    is
    0.54
    a
    0.52
    es
    0.52
     Shelby
    0.52
     نظ
    0.52
     Surg
    0.51
     Drew
    0.50
    vänt
    0.50
    Activations Density 0.008%

    No Known Activations