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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 4578
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and data structure manipulation

    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
    UnitTesting
    -0.88
    tagHelperRunner
    -0.87
    AndEndTag
    -0.79
    OGND
    -0.78
     betweenstory
    -0.77
     Италијани
    -0.76
     Biôgrafia
    -0.73
    évaluateur
    -0.70
    httphttps
    -0.68
     ***!
    -0.68
    POSITIVE LOGITS
     principales
    0.39
     affitto
    0.38
     annuel
    0.38
     name
    0.38
    name
    0.36
     conformidad
    0.35
     criteria
    0.35
    <0xE5>
    0.34
     location
    0.34
     parameters
    0.33
    Activations Density 1.026%

    No Known Activations