© 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. 12343
    Prev
    Next
    INDEX
    Explanations

    patterns of advanced formatting in the text

    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
     ve
    -0.90
     van
    -0.76
     sa
    -0.75
     M
    -0.75
     can
    -0.75
     de
    -0.73
     k
    -0.73
     v
    -0.72
     met
    -0.72
     r
    -0.71
    POSITIVE LOGITS
     Cæsar
    1.32
     itſelf
    1.29
     myſelf
    1.28
     Houſe
    1.19
     Diſ
    1.15
     doubtnut
    1.15
     Shakspeare
    1.15
     Monfieur
    1.14
     ſeveral
    1.12
     Escolar
    1.12
    Activations Density 0.189%

    No Known Activations