© 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. 4296
    Prev
    Next
    INDEX
    Explanations

    expressions related to pressure and its effects

    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
     AssemblyCulture
    -0.56
     skjer
    -0.42
    ity
    -0.38
    spreis
    -0.37
    tilor
    -0.37
    leştir
    -0.36
    mobileqq
    -0.36
    ybė
    -0.35
    帖最后由
    -0.34
    zusammen
    -0.34
    POSITIVE LOGITS
     cooker
    0.81
     exerted
    0.74
     Cooker
    0.68
     relief
    0.63
     Relief
    0.62
     relieving
    0.60
     relieved
    0.60
    relief
    0.57
    Relief
    0.57
    IVEREF
    0.54
    Activations Density 0.373%

    No Known Activations