© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13782
    Prev
    Next
    INDEX
    Explanations

    coding patterns related to buffer allocation and potential overflow vulnerabilities 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
     autorytatywna
    -0.43
    PreExecute
    -0.41
    İstinadlar
    -0.40
    
    -0.39
    iligung
    -0.39
    "}")
    -0.38
     flat
    -0.36
     Romana
    -0.36
    OGND
    -0.35
     fixed
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.52
    UrlResolution
    0.51
    AndEndTag
    0.47
    RenderAtEndOf
    0.46
    rungsseite
    0.46
    RefNanny
    0.46
     esternos
    0.44
    Circ
    0.43
    catering
    0.42
     EventArgs
    0.41
    Activations Density 0.709%

    No Known Activations