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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6150
    Prev
    Next
    INDEX
    Explanations

    phrases related to verification or checking

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

    instructions or suggestions to check or verify something (including references to checking docs or conditions)

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voordeel
    -0.55
    oas
    -0.51
     newUser
    -0.48
     publiek
    -0.48
    ourced
    -0.47
     imageUrl
    -0.47
    BorderLayout
    -0.47
    athus
    -0.47
    sterdam
    -0.46
     fileSize
    -0.46
    POSITIVE LOGITS
     check
    1.24
     Check
    1.24
    Check
    1.22
    check
    1.20
     CHECK
    1.15
    CHECK
    1.03
     Checker
    1.02
    ToCheck
    0.97
     Checks
    0.96
     checked
    0.95
    Activations Density 0.070%

    No Known Activations