Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1360
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and definition of data fields in a code or markup format

    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
    :✨
    -0.52
    Minimum
    -0.51
     Minimum
    -0.48
     فريبيس
    -0.47
    .*")]
    -0.47
     tranſ
    -0.47
     tute
    -0.45
     Highest
    -0.44
     autorytatywna
    -0.44
    minimum
    -0.43
    POSITIVE LOGITS
     max
    1.61
    max
    1.47
     Max
    1.30
    Max
    1.16
     min
    0.94
    マックス
    0.89
    min
    0.82
    MAX
    0.66
     MAX
    0.65
     maxed
    0.65
    Activations Density 0.140%

    No Known Activations