Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103077
    Prev
    Next
    INDEX
    Explanations

    programming constructs and terminology related to buffer overflow vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    VersionUID
    -0.63
    StructEnd
    -0.58
    msgTypes
    -0.56
    flashdata
    -0.52
    ChildScrollView
    -0.51
    новниш
    -0.49
    ">//
    -0.49
     footprints
    -0.48
    ]^{-
    -0.48
     jScrollPane
    -0.48
    POSITIVE LOGITS
     climbing
    0.47
     ddelweddau
    0.37
    climbing
    0.37
    UnitId
    0.35
     ویکی‌پدی
    0.34
     bluzka
    0.34
     řízení
    0.34
     spéciaux
    0.33
     CYCLE
    0.33
    Animated
    0.33
    Activations Density 0.001%

    No Known Activations