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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15744
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Geplaatst
    -0.37
     ente
    -0.33
     Vig
    -0.33
     Hoa
    -0.32
    Gemeinden
    -0.31
     EOF
    -0.30
     concor
    -0.28
    こんばんは
    -0.28
     Digital
    -0.27
     tip
    -0.27
    POSITIVE LOGITS
    rungsseite
    0.80
    WebVitals
    0.72
    parsedMessage
    0.71
    +#+#
    0.69
     GenerationType
    0.68
    setVerticalGroup
    0.66
    addPreferredGap
    0.63
    GEBURTSDATUM
    0.63
    RectangleBorder
    0.62
     fieltro
    0.60
    Activations Density 0.750%

    No Known Activations