© 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. 21-GEMMASCOPE-RES-16K
    6. 14072
    Prev
    Next
    INDEX
    Explanations

    elements related to image attributes in HTML

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.77
     beginnetje
    -0.68
    Personendaten
    -0.67
    UnusedPrivate
    -0.67
    сылкі
    -0.66
    AndEndTag
    -0.65
     ویکی‌پدیا
    -0.63
    PreExecute
    -0.63
    ViewImports
    -0.61
     endblock
    -0.61
    POSITIVE LOGITS
     alt
    1.10
    alt
    1.04
     src
    1.00
    src
    0.95
    Alt
    0.90
    ALT
    0.86
     Alt
    0.84
     height
    0.78
     ALT
    0.78
    height
    0.76
    Activations Density 0.183%

    No Known Activations