© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 82588
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "rolling."

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

    rolling news

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     betweenstory
    -0.62
     Réponses
    -0.52
     Japão
    -0.51
     thorax
    -0.50
    før
    -0.50
     Bewußt
    -0.49
     quæ
    -0.49
     vícti
    -0.48
     ब्रेकडाउन
    -0.48
     Itália
    -0.47
    POSITIVE LOGITS
     rolling
    2.19
     Rolling
    2.14
    Rolling
    2.05
    rolling
    1.82
     rolled
    1.15
    rolled
    1.07
    滚动
    0.96
     Rol
    0.83
    滚
    0.81
    Rol
    0.81
    Activations Density 0.008%

    No Known Activations