© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 524
    Prev
    Next
    INDEX
    Explanations

    keywords related to gaming, downloads, and digital content

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

    followed by citations

    np_acts-logits-general · gemini-2.0-flash

    election candidates, deep learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.62
    WithIOException
    -0.59
    tagHelperRunner
    -0.59
    uxxxx
    -0.57
    ніципа
    -0.56
    TagMode
    -0.53
    ſelf
    -0.52
    SourceChecksum
    -0.51
    enterOuterAlt
    -0.50
    RenderAtEndOf
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.36
    rawDesc
    0.35
     Roskov
    0.34
     Prinz
    0.31
     cred
    0.31
    WebElementEntity
    0.31
    GRANTED
    0.30
     poli
    0.30
    flashdata
    0.30
    ServiceTest
    0.30
    Activations Density 1.396%

    No Known Activations