© 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. 30-GEMMASCOPE-RES-16K
    11. 11469
    Prev
    Next
    INDEX
    Explanations

    mentions of functions and their behavior in coding and technology contexts

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

    frequency or repetition

    np_acts-logits-general · gemini-2.0-flash

    always and never

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.51
     InputDecoration
    -0.43
    inSlope
    -0.42
    ValueStyle
    -0.41
    TokenNameLBRACE
    -0.40
    HXLINE
    -0.40
    󠁧
    -0.39
    ="#"><
    -0.39
    ThroughAttribute
    -0.38
    SuccessListener
    -0.37
    POSITIVE LOGITS
     always
    3.34
    always
    3.03
     sempre
    2.84
     siempre
    2.83
     Always
    2.81
    Always
    2.81
     zawsze
    2.64
     всегда
    2.55
     never
    2.50
    siempre
    2.48
    Activations Density 1.034%

    No Known Activations