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. 14-GEMMASCOPE-RES-16K
    6. 2913
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or special codes in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.86
    numerusform
    -0.62
    niająca
    -0.61
    komme
    -0.58
    hasMoreElements
    -0.58
    &:
    -0.57
    .
    -0.57
     Datenschutzer
    -0.55
    posób
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    POSITIVE LOGITS
     خارجية
    0.66
    '));
    
    0.66
    |}\
    0.65
    %</
    0.63
    ''');
    0.63
     raiſ
    0.63
     ujednoznacz
    0.62
    ')));
    0.61
     }}"></
    0.61
    []
    
    0.60
    Activations Density 0.237%

    No Known Activations