© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121197
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technology and biology

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

    comics, raspberry, mitochondrial, Software, cannabin, electric, Mexico, super, LTE, MA, apoptosis, Indigenous

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    -0.78
     Administrativna
    -0.72
     mijne
    -0.68
    URLException
    -0.66
    ⟬
    -0.64
    writeFieldEnd
    -0.63
     Monfieur
    -0.58
     فريبيس
    -0.58
    onedDateTime
    -0.58
     zijne
    -0.57
    POSITIVE LOGITS
    jest
    0.29
    ature
    0.28
    sure
    0.28
     أيضًا
    0.28
    Toxic
    0.28
    Año
    0.27
    ßer
    0.27
     vnt
    0.27
    PO
    0.26
     rile
    0.26
    Activations Density 0.235%

    No Known Activations