© 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. 104688
    Prev
    Next
    INDEX
    Explanations

    concepts related to perspectives, views, and interpretations of societal issues

    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
    __":
    -0.78
     الحره
    -0.77
    __":
    -0.74
    IsMutable
    -0.73
     initComponents
    -0.67
    PyExc
    -0.66
     BoxFit
    -0.65
    WaitGroup
    -0.65
     AssemblyCulture
    -0.65
    URLException
    -0.65
    POSITIVE LOGITS
    anniversaire
    0.39
    כלי
    0.36
     fallas
    0.31
     lists
    0.31
     czego
    0.31
    頃の
    0.31
     aplicable
    0.31
     tendencies
    0.30
     experience
    0.30
     makna
    0.30
    Activations Density 0.062%

    No Known Activations