© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14868
    Prev
    Next
    INDEX
    Explanations

    terms related to performance metrics and compliance in technical contexts

    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
    +#+#
    -0.64
    gonic
    -0.59
    AuthProvider
    -0.56
     GoogleFonts
    -0.56
    SOUNDBITE
    -0.54
     الرخصة
    -0.54
     plagioclase
    -0.54
    migrationBuilder
    -0.53
     intptr
    -0.53
    таратура
    -0.53
    POSITIVE LOGITS
     levels
    1.46
     level
    1.44
     rate
    1.30
     rates
    1.10
    levels
    1.08
    level
    1.08
     Levels
    1.03
     ratio
    1.03
     LEVELS
    1.00
    niveau
    0.96
    Activations Density 1.307%

    No Known Activations