© 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. 7453
    Prev
    Next
    INDEX
    Explanations

    syntax and punctuation in code

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

    Code snippets with bracketed variables or values

    np_acts-logits-general · gemini-2.0-flash

    code structure and punctuation

    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
    Datuak
    -0.43
    ↵
    -0.33
    )』
    -0.31
    CM
    -0.31
    >>();
    -0.28
     dia
    -0.28
    Trusted
    -0.28
    request
    -0.28
     CM
    -0.28
    )」
    -0.28
    POSITIVE LOGITS
    expandindo
    0.91
    TypedDataSet
    0.79
    rungsseite
    0.75
    writeFieldEnd
    0.72
    WireFormatLite
    0.72
    styleType
    0.71
    antMatchers
    0.70
    SpringRunner
    0.69
    <unused43>
    0.68
    posedge
    0.68
    Activations Density 0.421%

    No Known Activations