© 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. 94916
    Prev
    Next
    INDEX
    Explanations

    the presence of whitespace or gaps in the text

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

    numbers, years, and quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    instances of a specific nonstandard Unicode space character (a narrow/thin space) in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    MessageTagHelper
    -0.64
    XmlAccessType
    -0.56
     newBuilder
    -0.49
    sizeCache
    -0.41
    UserScript
    -0.41
    +:+
    -0.40
    RTEE
    -0.39
    دانشنامهٔ
    -0.38
    setVerticalGroup
    -0.37
    featureID
    -0.37
    POSITIVE LOGITS
     zwiſchen
    0.70
     dieſes
    0.68
    <unused28>
    0.66
    <unused14>
    0.66
    <unused51>
    0.66
    <unused41>
    0.66
    <pad>
    0.66
    <unused23>
    0.66
    <unused16>
    0.66
    [@BOS@]
    0.66
    Activations Density 0.038%

    No Known Activations