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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 10025
    Prev
    Next
    INDEX
    Explanations

    negations and terms related to dissent or disagreement

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

    "of" or "_" in code/data

    np_acts-logits-general · gemini-2.0-flash

    code structure with underscore

    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
     argint
    -0.43
     corrientes
    -0.42
     vectorielles
    -0.40
     gră
    -0.38
     băr
    -0.38
     înt
    -0.38
     científicas
    -0.37
     courants
    -0.37
     conclusão
    -0.36
     uș
    -0.36
    POSITIVE LOGITS
    ruik
    0.53
    ніципалі
    0.52
    SBATCH
    0.51
    XmlEnum
    0.50
     typelib
    0.49
    endpush
    0.49
    InputBorder
    0.48
    EndGlobalSection
    0.47
    ########.
    0.47
    Transcription
    0.47
    Activations Density 0.074%

    No Known Activations