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. 57304
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of potentiality or uncertainty

    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
    ItemBackground
    -0.88
    transQ
    -0.75
     AssemblyCompany
    -0.74
     '\\;'
    -0.73
     мәкал
    -0.72
    aarrggbb
    -0.72
    pantalones
    -0.71
     ujednoznacz
    -0.70
    IntoConstraints
    -0.69
     Italijani
    -0.68
    POSITIVE LOGITS
     penta
    0.28
    ืน
    0.28
    zed
    0.27
    CreateInfo
    0.27
    It
    0.27
    /
    0.25
    chenkt
    0.24
    :
    0.24
    ans
    0.23
    ator
    0.23
    Activations Density 0.149%

    No Known Activations