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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5356
    Prev
    Next
    INDEX
    Explanations

    relationships between variables in a statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.42
    DOCTYPE
    -0.41
    fromCharCode
    -0.38
    hasMoreElements
    -0.36
    borderBottom
    -0.36
    gnan
    -0.34
    mitas
    -0.33
     Aircraft
    -0.32
     peg
    -0.32
     Atta
    -0.32
    POSITIVE LOGITS
    RenderAtEndOf
    0.74
    RunWith
    0.64
     ModelExpression
    0.60
    IntoConstraints
    0.60
     desmotivaciones
    0.56
    HasForeignKey
    0.54
    ArgumentParser
    0.54
    LookAnd
    0.53
    oredCriteria
    0.53
    XmlAccessorType
    0.51
    Activations Density 2.180%

    No Known Activations