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. 22426
    Prev
    Next
    INDEX
    Explanations

    terms related to the structure and components of physical objects or mechanisms

    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
    webElementXpaths
    -0.59
    WebElementEntity
    -0.58
    DockStyle
    -0.55
    Occurred
    -0.51
    ″]
    -0.51
    DebuggerStep
    -0.51
    AndroidJUnit
    -0.50
    ᅠ
    -0.49
    ape
    -0.49
    Personensuche
    -0.47
    POSITIVE LOGITS
    InputBorder
    0.43
     Infór
    0.42
     BoxDecoration
    0.42
     normalidad
    0.40
    esterno
    0.40
     stationnement
    0.37
     setempat
    0.37
     mystère
    0.36
     finanzas
    0.36
    الدراسه
    0.36
    Activations Density 0.073%

    No Known Activations