© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2818
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" and its variations, indicating reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.76
    AddTagHelper
    -0.71
     ExecuteAsync
    -0.69
    enterOuterAlt
    -0.67
     JpaRepository
    -0.67
    bootstrapcdn
    -0.65
    jooq
    -0.63
     AppCompatTheme
    -0.60
    TargetException
    -0.60
    ㈯
    -0.60
    POSITIVE LOGITS
     said
    0.68
     peuples
    0.39
     sagte
    0.37
     dijo
    0.36
     avoient
    0.35
     katanya
    0.35
     improve
    0.33
     says
    0.33
     regeringen
    0.32
     dabei
    0.32
    Activations Density 0.456%

    No Known Activations