© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11583
    Prev
    Next
    INDEX
    Explanations

    references to online and physical store contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FunctionFlags
    -0.64
    IndentedString
    -0.64
    scholars
    -0.61
    WebElementEntity
    -0.54
     Италијани
    -0.53
    RegressionTest
    -0.51
    ɵɵelementEnd
    -0.48
    InSection
    -0.48
    #+#
    -0.47
    OGND
    -0.47
    POSITIVE LOGITS
     store
    2.73
    store
    2.36
     Store
    2.31
    Store
    2.16
     STORE
    2.09
     stores
    1.91
    STORE
    1.87
     Stores
    1.65
    stores
    1.55
    getStore
    1.55
    Activations Density 0.370%

    No Known Activations