© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7168
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     Outcomes
    -0.84
     outcomes
    -0.82
    outcomes
    -0.81
    Outcomes
    -0.79
     OUTCOMES
    -0.69
     Findings
    -0.67
     Outputs
    -0.66
     outputs
    -0.65
     informée
    -0.62
    Findings
    -0.61
    POSITIVE LOGITS
     result
    2.20
    result
    2.05
     Result
    1.49
    Result
    1.48
     RESULT
    1.31
     résultat
    1.21
     resul
    1.20
     resulta
    1.18
     resultar
    1.14
    RESULT
    1.13
    Activations Density 0.339%

    No Known Activations