© 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. 37-GEMMASCOPE-RES-16K
    11. 4904
    Prev
    Next
    INDEX
    Explanations

    documents and reports that include visual data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.36
    rrggbb
    -0.35
    ----</
    -0.34
    URLException
    -0.34
     Studied
    -0.34
    comings
    -0.33
     ddelweddau
    -0.33
    舺
    -0.33
     buurt
    -0.31
    mindedness
    -0.31
    POSITIVE LOGITS
     describing
    1.70
     depicting
    1.62
     detailing
    1.55
     explaining
    1.55
     indicating
    1.49
     outlining
    1.48
     showing
    1.45
     announcing
    1.44
     documenting
    1.40
     denoting
    1.40
    Activations Density 2.322%

    No Known Activations