© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4938
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical concepts and devices

    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
    ized
    -0.90
    Zel
    -0.71
    DNEY
    -0.71
    <h6>
    -0.70
    haften
    -0.69
    <s>
    -0.68
     Bernal
    -0.68
    ied
    -0.67
    itized
    -0.67
    URIS
    -0.67
    POSITIVE LOGITS
    s
    1.12
     Dinah
    0.91
    ToolStripButton
    0.85
    hhhhhhhh
    0.84
     وتسجيلات
    0.84
    GenerationType
    0.82
     Infórmanos
    0.81
    WithIOException
    0.81
     חיצוניים
    0.80
     ویکی‌آمباردا
    0.79
    Activations Density 0.541%

    No Known Activations