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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3916
    Prev
    Next
    INDEX
    Explanations

    statistical analysis results and mentions of ethical considerations in studies

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

    Section or subsection labels

    np_acts-logits-general · gemini-2.0-flash

    section headings with numbers

    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
    новниш
    -0.66
     חיצוניים
    -0.54
    #+#
    -0.51
    :✨
    -0.50
    EDEFAULT
    -0.49
     lenker
    -0.47
    Rüyada
    -0.47
    Legături
    -0.46
    ècie
    -0.45
    EndContext
    -0.44
    POSITIVE LOGITS
    IANA
    0.39
    endregion
    0.39
    Conclusion
    0.37
    GeneratedCode
    0.37
     Discussion
    0.37
     discussion
    0.36
    endmodule
    0.35
    LEncoder
    0.35
    principalTable
    0.35
     methodology
    0.34
    Activations Density 0.752%

    No Known Activations