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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 15711
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operations

    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
    説明
    -0.29
    igshid
    -0.29
    per
    -0.28
     konus
    -0.28
     تد
    -0.26
     siden
    -0.26
    id
    -0.25
     indeed
    -0.24
    token
    -0.24
    ↵↵
    -0.24
    POSITIVE LOGITS
     stiefe
    0.87
    iſchen
    0.87
     beſte
    0.86
    <unused74>
    0.85
    <unused47>
    0.85
    <unused17>
    0.85
    <unused8>
    0.85
    <unused14>
    0.85
    <unused3>
    0.85
    [@BOS@]
    0.85
    Activations Density 4.536%

    No Known Activations