© 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. 27-GEMMASCOPE-RES-16K
    11. 9899
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their connections in sentences

    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
    CROSSTALK
    -0.44
    Kanpo
    -0.32
     sillä
    -0.31
     nonUne
    -0.30
    ?&
    -0.30
    isBlank
    -0.30
    ihnach
    -0.29
     AssemblyCulture
    -0.29
     :)
    -0.29
     Bré
    -0.28
    POSITIVE LOGITS
    المناصب
    0.59
    enumii
    0.56
    ThroughAttribute
    0.54
     informée
    0.54
    ChrTalk
    0.53
    RegressionTest
    0.52
     '\\;'
    0.50
    帯
    0.49
     ब्रेकडाउन
    0.49
    gamot
    0.48
    Activations Density 0.377%

    No Known Activations