© 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. 23-GEMMASCOPE-RES-16K
    11. 4733
    Prev
    Next
    INDEX
    Explanations

    structured code blocks or function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BibitemShut
    -0.67
     وتسجيلات
    -0.59
    vikle
    -0.59
    OGND
    -0.58
    duled
    -0.57
    ſtanding
    -0.55
    euvre
    -0.54
    gean
    -0.54
    bibfield
    -0.54
    leſs
    -0.53
    POSITIVE LOGITS
    Hozzáférés
    0.70
    awaiter
    0.68
    ConstraintMaker
    0.64
    \{\\
    0.63
    SourceChecksum
    0.62
    rawDesc
    0.59
    !*\
    0.58
    <unused63>
    0.58
    //
    0.57
     surla
    0.57
    Activations Density 0.064%

    No Known Activations