© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10764
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical compound "ale."

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

    ending in "le," "ile," or a similar suffix

    np_acts-logits-general · gemini-2.0-flash

    code-related or name endings

    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
     réfrig
    -0.32
    Gap
    -0.32
    Viewport
    -0.31
     outono
    -0.31
    timmt
    -0.31
    TARGET
    -0.30
    Garantie
    -0.30
     zv
    -0.30
    ص
    -0.30
     Gerechtigkeit
    -0.29
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
     ModelExpression
    0.66
     للمعارف
    0.63
    SharedCtor
    0.62
    tagHelperRunner
    0.60
    <?
    0.57
    uxxxx
    0.55
     تكبرها
    0.54
     فريبيس
    0.53
    TagMode
    0.52
    Activations Density 0.275%

    No Known Activations