© 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. 3-GEMMASCOPE-RES-16K
    11. 11406
    Prev
    Next
    INDEX
    Explanations

    the keyword "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.75
     programme
    -0.72
    
    -0.71
    ➜
    -0.70
    ))->
    -0.70
     manoeuvre
    -0.68
    programme
    -0.68
    Programme
    -0.68
     Ferne
    -0.67
     Narayan
    -0.67
    POSITIVE LOGITS
    all
    2.13
     all
    1.90
    ALL
    1.88
    All
    1.81
     ALL
    1.80
     All
    1.79
     GetAll
    1.48
     getAll
    1.42
    getAll
    1.42
    alls
    1.36
    Activations Density 0.144%

    No Known Activations