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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1779
    Prev
    Next
    INDEX
    Explanations

    terms related to selection processes in genetic studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecake
    -0.84
     errMsg
    -0.81
    quations
    -0.80
    karz
    -0.79
    EObject
    -0.79
     bytu
    -0.79
     Audiodateien
    -0.75
     cwd
    -0.74
     surla
    -0.74
     Penh
    -0.73
    POSITIVE LOGITS
     Sele
    1.39
     Selections
    1.37
     Selection
    1.30
     selections
    1.30
     selection
    1.26
    Selection
    1.23
    Sele
    1.22
     sele
    1.18
    selection
    1.15
    setSelection
    1.12
    Activations Density 0.040%

    No Known Activations