© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    corporate roles and responsibilities

    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
    ########.
    -0.51
    providedIn
    -0.49
    脚注の使い方
    -0.49
     république
    -0.45
    CreateMap
    -0.44
     priorité
    -0.43
    CrossRef
    -0.42
     Carthage
    -0.42
     spé
    -0.41
     współpra
    -0.41
    POSITIVE LOGITS
     marketing
    1.46
     Marketing
    1.24
    marketing
    1.24
    Marketing
    1.17
     logistics
    1.16
     administrative
    1.15
     finance
    1.08
     administration
    1.03
     MARKETING
    1.02
     HR
    1.00
    Activations Density 0.298%

    No Known Activations