© 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. 7135
    Prev
    Next
    INDEX
    Explanations

    conditional or hypothetical statements and their implications

    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
    不太
    -0.33
     GetEnumerator
    -0.32
    IndentedString
    -0.31
     TextInputType
    -0.30
    却又
    -0.30
    disposing
    -0.29
     determin
    -0.28
    Espèce
    -0.28
    glLoadIdentity
    -0.27
    ValueGenerated
    -0.27
    POSITIVE LOGITS
     trust
    2.09
    trust
    1.88
     believe
    1.84
    Trust
    1.82
     Trust
    1.77
    Believe
    1.73
     Believe
    1.71
    believe
    1.71
     TRUST
    1.60
    TRUST
    1.47
    Activations Density 0.475%

    No Known Activations