© 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. 37-GEMMASCOPE-RES-16K
    6. 5390
    Prev
    Next
    INDEX
    Explanations

    programming and layout-related terminology

    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
     alianza
    -0.41
    dessous
    -0.38
    mtrl
    -0.37
     tenaga
    -0.37
     trayectoria
    -0.35
     누
    -0.35
    Dónde
    -0.35
     kautta
    -0.34
     desecha
    -0.34
    Farbe
    -0.33
    POSITIVE LOGITS
     width
    0.99
     Width
    0.93
     aspect
    0.83
     pixel
    0.83
     resolution
    0.82
     widths
    0.80
     Aspect
    0.79
    Width
    0.77
    width
    0.77
     Resolution
    0.77
    Activations Density 0.399%

    No Known Activations