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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6747
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to adjustments and controls in technical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     AspNetCore
    -0.66
    enumi
    -0.57
    LLocation
    -0.57
    DropTable
    -0.56
    tableFuture
    -0.55
    tagHelper
    -0.54
    nextLine
    -0.54
    ongono
    -0.54
    toPromise
    -0.53
    RUnlock
    -0.53
    POSITIVE LOGITS
     adjustment
    1.40
     adjust
    1.34
     adjusting
    1.26
     adjustments
    1.24
     adjustable
    1.23
     adjusts
    1.21
     Adjust
    1.20
     Adjustment
    1.17
    Adjust
    1.16
     adjusted
    1.14
    Activations Density 0.626%

    No Known Activations