© 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. 11-GEMMASCOPE-RES-16K
    11. 13046
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurement or quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.88
    ScopeManager
    -0.87
    providedIn
    -0.85
    tvguidetime
    -0.83
    }))
    -0.81
     Chwiliwch
    -0.80
    IsContent
    -0.77
    adaptiveStyles
    -0.76
     pinulongan
    -0.74
    RectangleBorder
    -0.73
    POSITIVE LOGITS
    opus
    0.51
     plus
    0.48
    fcntl
    0.42
    êche
    0.42
    ware
    0.42
     geldig
    0.41
     seg
    0.41
     North
    0.40
    ;
    0.39
     alone
    0.39
    Activations Density 0.944%

    No Known Activations