© 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. 9-GEMMASCOPE-RES-16K
    11. 9371
    Prev
    Next
    INDEX
    Explanations

    references to document creation and copyright information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.63
     betweenstory
    -0.62
    RegressionTest
    -0.60
    ChildScrollView
    -0.53
     виправивши
    -0.48
    endmodule
    -0.47
    tinyos
    -0.46
     Paglinawan
    -0.44
     Italijanski
    -0.42
    acyjny
    -0.41
    POSITIVE LOGITS
    addCriterion
    1.68
     <=",
    0.71
     يتيمه
    0.63
    matchCondition
    0.54
    TextBoxColumn
    0.54
     JAXBElement
    0.51
     <>",
    0.51
    Personendaten
    0.47
    setopt
    0.46
    IntoConstraints
    0.44
    Activations Density 0.019%

    No Known Activations