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. 12-GEMMASCOPE-RES-16K
    6. 11935
    Prev
    Next
    INDEX
    Explanations

    phrases that involve raising or increasing awareness, funds, or support, particularly for children or important issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.03
    continent
    -0.80
    onov
    -0.79
     CURIAM
    -0.78
    loem
    -0.71
     Bett
    -0.71
     Macao
    -0.70
     للمعارف
    -0.70
     ciutat
    -0.69
     Padova
    -0.69
    POSITIVE LOGITS
     Raise
    1.44
    raised
    1.39
    Raise
    1.39
     raised
    1.37
     raise
    1.37
     raising
    1.33
     Raising
    1.32
     raises
    1.31
     Raises
    1.26
    raise
    1.26
    Activations Density 0.086%

    No Known Activations