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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8891
    Prev
    Next
    INDEX
    Explanations

    actions and occurrences of falling or being thrown

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    falling and slipping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     CreateTagHelper
    -0.37
    toral
    -0.36
     agré
    -0.34
    CloseHandle
    -0.33
    hfill
    -0.33
     nhật
    -0.32
    setupUi
    -0.31
    ₎
    -0.31
     kasarigan
    -0.31
    </thead>
    -0.30
    POSITIVE LOGITS
    yntaxException
    0.71
    accident
    0.63
     caduta
    0.60
     caída
    0.60
     ACCIDENT
    0.59
     jatuh
    0.59
    Falling
    0.57
     mishap
    0.56
     accident
    0.56
    摔
    0.56
    Activations Density 0.023%

    No Known Activations