© 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. 9-GEMMASCOPE-RES-16K
    11. 7184
    Prev
    Next
    INDEX
    Explanations

    sections of texts that summarize content and provide methodological insights

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

    Introductions to sections

    np_acts-logits-general · gemini-2.0-flash

    section of the text

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    exitRule
    -0.47
    UMBUS
    -0.42
    ifoli
    -0.40
     isComment
    -0.39
    нрави
    -0.39
    opedic
    -0.38
     Observer
    -0.38
     Majestic
    -0.38
    rawDesc
    -0.38
    matchCondition
    -0.37
    POSITIVE LOGITS
    mybatisplus
    0.58
    BeginInit
    0.57
     незавершена
    0.52
    évaluateur
    0.48
    EndInit
    0.47
    archiviato
    0.47
    ContentAlignment
    0.47
    ViewImports
    0.47
    abstractmethod
    0.44
    UpInside
    0.44
    Activations Density 0.802%

    No Known Activations