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. 51934
    Prev
    Next
    INDEX
    Explanations

    themes of family obligation and perceived responsibilities

    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-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
     project
    -0.37
    anus
    -0.37
     Project
    -0.37
     Guards
    -0.36
    пут
    -0.36
    utro
    -0.35
     Circuit
    -0.35
     die
    -0.35
     Witten
    -0.35
    kter
    -0.34
    POSITIVE LOGITS
    +#+#
    0.59
     AssemblyCompany
    0.56
    новниш
    0.51
    exitRule
    0.49
    ंदीखरीदारी
    0.48
     Италијани
    0.47
    AndEndTag
    0.46
    ScopeManager
    0.46
     moindre
    0.44
    WillAppear
    0.44
    Activations Density 0.046%

    No Known Activations