© 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. 9-GEMMASCOPE-RES-131K
    11. 66068
    Prev
    Next
    INDEX
    Explanations

    discourse markers that indicate argumentation and critique of societal issues

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

    specific names or entities

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

    It detects words at the start of sentences (sentence-initial tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noti
    -0.41
    notice
    -0.40
    moder
    -0.40
     multil
    -0.40
     Exper
    -0.40
     diag
    -0.39
    solo
    -0.39
     statis
    -0.38
    cute
    -0.38
    ساز
    -0.38
    POSITIVE LOGITS
    BufferException
    0.56
    richTextPanel
    0.55
    setVerticalGroup
    0.53
    StructEnd
    0.52
    jenige
    0.51
     magnétique
    0.50
     arguing
    0.49
    ToAction
    0.49
     propOrder
    0.47
    MessageOf
    0.46
    Activations Density 0.313%

    No Known Activations