© 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. 38-GEMMASCOPE-RES-16K
    11. 13542
    Prev
    Next
    INDEX
    Explanations

    phrases that imply degrees or extents of comparison or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.91
    __':
    -0.88
     <<<<<<<<<<<<<<
    -0.85
     Wiktionnaire
    -0.84
    \{\\
    -0.84
    transQ
    -0.83
    ロウィン
    -0.83
    parsedMessage
    -0.82
    __":
    -0.82
    MessageState
    -0.82
    POSITIVE LOGITS
     measure
    0.48
     point
    0.47
     part
    0.44
     account
    0.44
     deal
    0.44
     pace
    0.43
     token
    0.42
     path
    0.40
    ↵↵
    0.39
     time
    0.38
    Activations Density 0.297%

    No Known Activations