© 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. 4850
    Prev
    Next
    INDEX
    Explanations

    variables and their declarations or assignments in programming code

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

    Variable or parameter names

    np_acts-logits-general · gemini-2.0-flash

    variable assignment or code block

    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
    الحياه
    -0.67
    in
    -0.45
    сшта
    -0.43
    queles
    -0.43
    harusnya
    -0.41
     Große
    -0.41
    Välislingid
    -0.40
    zule
    -0.40
    //</
    -0.39
    gå
    -0.39
    POSITIVE LOGITS
    <bos>
    0.63
     getB
    0.58
     defaultstate
    0.56
     getF
    0.52
     getS
    0.51
    getB
    0.51
     getP
    0.51
     getM
    0.51
    gatsby
    0.50
     nakalista
    0.49
    Activations Density 3.510%

    No Known Activations