© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15590
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements, particularly around function calls and statements 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
    SuspendLayout
    -0.50
     hObject
    -0.50
     sypial
    -0.49
    expandindo
    -0.47
     zoude
    -0.46
     transparan
    -0.46
    pation
    -0.46
    internalType
    -0.45
     miniaturka
    -0.45
     comigo
    -0.44
    POSITIVE LOGITS
    NamedQueries
    0.49
    تقاوى
    0.46
    oa̍t
    0.42
    optionalTypeArgs
    0.41
    BarStyle
    0.40
    ్రామ
    0.40
    #+#
    0.39
    SequentialGroup
    0.38
    @[+][
    0.37
    goto
    0.35
    Activations Density 0.144%

    No Known Activations