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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 5923
    Prev
    Next
    INDEX
    Explanations

    percentage symbols and related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Percentage signs followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    % formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \"></
    -0.73
    GGLE
    -0.70
    dzie
    -0.70
    🏻
    -0.69
    ;*/
    -0.68
     mati
    -0.66
     tret
    -0.66
    lias
    -0.65
     byd
    -0.64
    secta
    -0.64
    POSITIVE LOGITS
    ("%
    1.13
     %
    1.11
     \%$
    1.11
    ="%
    1.09
     \%
    1.06
    -%
    1.04
    }%
    1.03
    %
    1.03
    ,"%
    0.96
    ('%
    0.95
    Activations Density 0.224%

    No Known Activations