© 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. 28-GEMMASCOPE-RES-16K
    6. 9016
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to data processing in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C++ or Python code syntax

    np_acts-logits-general · gemini-2.0-flash

    . or :: followed by code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.52
    Попис
    -0.51
    OCCURRED
    -0.47
    hdashline
    -0.47
    parsedMessage
    -0.45
     Autorizaciones
    -0.45
     referenties
    -0.44
    ніципа
    -0.44
    InsertCommand
    -0.43
    kháu
    -0.43
    POSITIVE LOGITS
     SDLK
    0.40
    شهاد
    0.39
     kobiet
    0.37
    OGND
    0.37
     conjunta
    0.35
    lasses
    0.35
     العاده
    0.35
    viewDid
    0.34
     Alliance
    0.33
    PDOException
    0.33
    Activations Density 0.160%

    No Known Activations