© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9984
    Prev
    Next
    INDEX
    Explanations

    references to various types of documents or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     déplacement
    -0.29
    har
    -0.28
     modest
    -0.28
     simple
    -0.28
     réalisation
    -0.28
     moment
    -0.26
     colgante
    -0.26
     comunità
    -0.26
     vicenda
    -0.26
     industriales
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.90
    DockStyle
    0.89
    IntoConstraints
    0.85
    MLLoader
    0.82
    ChildScrollView
    0.82
     للاسماء
    0.77
    AndEndTag
    0.75
    ScopeManager
    0.75
    setVerticalGroup
    0.75
    OGND
    0.74
    Activations Density 0.559%

    No Known Activations