© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104585
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives related to personal emotions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.35
     positivos
    -0.34
     normally
    -0.33
     directivos
    -0.33
     initComponents
    -0.33
     vzd
    -0.32
    Спољашње
    -0.32
    Fordítás
    -0.32
    )};
    -0.32
     Wortes
    -0.32
    POSITIVE LOGITS
    Clik
    0.59
    锈钢
    0.59
     незавершена
    0.56
    saraba
    0.55
    XtraReports
    0.54
     Italijani
    0.53
     ModelExpression
    0.53
     Italijanski
    0.52
    NameInMap
    0.52
    Vidite
    0.52
    Activations Density 0.000%

    No Known Activations