© 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. 7250
    Prev
    Next
    INDEX
    Explanations

    terms related to requirements and the need for certain criteria or components

    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
     möjligt
    -0.53
     possibilities
    -0.49
     automatically
    -0.47
    ApiModelProperty
    -0.46
     mögliche
    -0.46
     useful
    -0.45
    useful
    -0.45
     bermanfaat
    -0.44
     agrí
    -0.44
     possibile
    -0.42
    POSITIVE LOGITS
     careful
    1.02
     patience
    0.93
     Careful
    0.76
    才行
    0.74
    Careful
    0.73
     paciencia
    0.73
     special
    0.71
     Patience
    0.70
     considerable
    0.69
    patience
    0.69
    Activations Density 0.748%

    No Known Activations