© 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. 13494
    Prev
    Next
    INDEX
    Explanations

    references to figures, panels, or visual representations in a structured document context

    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
    UrlResolution
    -0.37
    ]<<"
    -0.35
     forbear
    -0.33
    schra
    -0.32
    oa̍t
    -0.32
     Kirkwood
    -0.32
    saraba
    -0.32
    OGND
    -0.31
     Piles
    -0.31
    }{*}{
    -0.31
    POSITIVE LOGITS
     panel
    3.72
     Panel
    3.44
     panels
    3.19
    panel
    3.17
    Panel
    3.11
     PANEL
    3.08
     Panels
    2.92
    PANEL
    2.78
     paneles
    2.67
    panels
    2.63
    Activations Density 1.108%

    No Known Activations