© 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. 7967
    Prev
    Next
    INDEX
    Explanations

    elements related to coding functions and structures in programming

    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
    4
    -0.30
    WriteAttribute
    -0.28
    2
    -0.26
     Vorstellungen
    -0.24
     Dank
    -0.24
    inição
    -0.23
     niega
    -0.22
    区
    -0.21
     Wikiseite
    -0.21
     Grüßen
    -0.21
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    tagHelperRunner
    0.78
     surla
    0.75
     informée
    0.75
    <unused43>
    0.75
    <unused79>
    0.74
    Autoritní
    0.74
    <unused8>
    0.74
    <unused3>
    0.74
    <pad>
    0.74
    Activations Density 0.178%

    No Known Activations