© 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. 96126
    Prev
    Next
    INDEX
    Explanations

    references to specific software or versions within a technical context

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

    file hashes and security algorithms

    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
    XtraEditors
    -0.51
    setupUi
    -0.51
    BagConstraints
    -0.50
     كومونز
    -0.50
     initComponents
    -0.47
    contentPane
    -0.47
    PropertyChanging
    -0.46
     समीक्षक
    -0.45
    EndContext
    -0.45
     makeStyles
    -0.42
    POSITIVE LOGITS
    ">//
    0.75
    出版年
    0.47
     surla
    0.44
    corpions
    0.42
     evt
    0.41
     Scorpion
    0.39
    原始内容存档于
    0.39
    cshtml
    0.39
     discul
    0.38
    OGND
    0.37
    Activations Density 0.001%

    No Known Activations