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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 35568
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to clearing, removing, or deleting items or data in programming

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

    delete, rm, clean, close, death

    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
    pushFollow
    -0.39
    #+#
    -0.36
    ✭✭
    -0.34
    audiovisuel
    -0.33
     novio
    -0.33
     surla
    -0.32
    Inspection
    -0.31
     datab
    -0.31
     devrez
    -0.29
    淹
    -0.29
    POSITIVE LOGITS
    PreExecute
    0.63
    suicide
    0.49
    CloseOperation
    0.49
    clean
    0.47
    rmtree
    0.47
    олові
    0.46
    strick
    0.45
    ousand
    0.45
    death
    0.45
     içi
    0.44
    Activations Density 0.014%

    No Known Activations