© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 861
    Prev
    Next
    INDEX
    Explanations

    mentions of academic or scientific identifiers related to author names or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pure
    -0.30
    لينكات
    -0.30
    zete
    -0.29
    Literatur
    -0.27
     pure
    -0.27
     sky
    -0.27
    des
    -0.26
     PURE
    -0.26
    Einzelnachweise
    -0.26
    Desc
    -0.26
    POSITIVE LOGITS
    ConstraintMaker
    0.58
    rsiniz
    0.57
     protoimpl
    0.57
    +#+#
    0.54
     HasFactory
    0.54
    makeConstraints
    0.53
    vician
    0.53
    :✨
    0.53
     initComponents
    0.53
    ScopeManager
    0.51
    Activations Density 0.332%

    No Known Activations