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. 7349
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs in code syntax

    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
    RegistryLite
    -0.54
    douard
    -0.51
     Auflage
    -0.51
     infantiles
    -0.50
     sahiptir
    -0.49
    printStackTrace
    -0.49
    bacher
    -0.49
     maglia
    -0.48
    sidemargin
    -0.48
     defStyleAttr
    -0.48
    POSITIVE LOGITS
    ($"
    0.76
    ($"{
    0.75
     AspNetCore
    0.75
    migrationBuilder
    0.74
     ReSharper
    0.73
    //
    0.71
     Culture
    0.67
    TagHelper
    0.66
     ExecuteAsync
    0.65
     culture
    0.64
    Activations Density 0.960%

    No Known Activations