Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6520
    Prev
    Next
    INDEX
    Explanations

    the scientific or technical terminology related to systems and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اشة
    -0.58
     Réponses
    -0.56
     focal
    -0.55
    ThroughAttribute
    -0.53
    atisk
    -0.53
    archiviato
    -0.51
     Gow
    -0.51
     surla
    -0.50
    Titled
    -0.48
    utsches
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.58
    sizeCache
    0.58
    RectangleBorder
    0.54
     mxArray
    0.54
     Mahomet
    0.53
    principalColumn
    0.52
    KommentareTeilen
    0.51
    </thead>
    0.51
    Personensuche
    0.51
    #+#
    0.49
    Activations Density 1.038%

    No Known Activations