Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7486
    Prev
    Next
    INDEX
    Explanations

    affirmative statements regarding the existence or presence of specific issues or entities

    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
    InjectAttribute
    -0.40
    Kjelder
    -0.39
    InstrumentedTest
    -0.34
    ế
    -0.33
     gee
    -0.33
    ジェラ
    -0.33
    ==
    -0.32
     Cli
    -0.31
    tedly
    -0.31
     gel
    -0.30
    POSITIVE LOGITS
     initComponents
    0.77
     cauſe
    0.77
     cause
    0.71
     reason
    0.71
     anledning
    0.70
     caufe
    0.68
    Cause
    0.67
     CAUSE
    0.66
    cause
    0.65
     razões
    0.61
    Activations Density 0.472%

    No Known Activations