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. 7551
    Prev
    Next
    INDEX
    Explanations

    details related to social interactions and the impact of body language and appearance on professional perception

    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
    parsedMessage
    -0.85
    OrBuilder
    -0.71
     <>",
    -0.69
    RenderAtEndOf
    -0.63
    ///</
    -0.61
    ADELPHIA
    -0.61
    CppMethod
    -0.60
     تضيفلها
    -0.58
     acteurs
    -0.57
    GeneratedMessage
    -0.57
    POSITIVE LOGITS
     signal
    0.60
    мерть
    0.52
     profile
    0.52
    ピール
    0.51
     lá
    0.47
    CODES
    0.47
    graphed
    0.45
     signaler
    0.44
     Signal
    0.44
     sinal
    0.43
    Activations Density 0.425%

    No Known Activations