Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9279
    Prev
    Next
    INDEX
    Explanations

    words indicating caution or alertness 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.80
     Roskov
    -0.78
     >=",
    -0.72
     BorderSide
    -0.72
    ölkerung
    -0.71
    RegistryLite
    -0.71
    :✨
    -0.71
    onnay
    -0.70
     &___
    -0.70
    tagHelperRunner
    -0.69
    POSITIVE LOGITS
    ')):
    0.47
     том
    0.43
    }))
    
    0.42
     тому
    0.41
     Voilà
    0.40
    >>()
    0.40
     Talon
    0.40
    >())
    0.40
    })->
    0.39
     GIPHY
    0.39
    Activations Density 0.042%

    No Known Activations