© 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. 10-GEMMASCOPE-RES-16K
    11. 4361
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and percentages in data reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.78
    ագրություններ
    -0.77
     виправивши
    -0.75
    __":
    -0.72
     nahilalakip
    -0.71
     ujednoznacz
    -0.68
    +#+#
    -0.66
    findpost
    -0.65
    SharedCtor
    -0.62
    Bronnen
    -0.61
    POSITIVE LOGITS
     (%)
    1.08
     percentage
    0.98
     percent
    0.96
    (%)
    0.96
     (\%)
    0.95
     Prozent
    0.93
     Percent
    0.92
     $(\%)$
    0.92
    percentage
    0.90
    %
    0.87
    Activations Density 0.613%

    No Known Activations