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. 8-GEMMASCOPE-RES-16K
    6. 4627
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of raising or increasing something, focusing specifically on awareness and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -1.01
     CURIAM
    -0.86
    continent
    -0.78
    otide
    -0.74
    onov
    -0.74
     Bett
    -0.72
    ürtel
    -0.70
    mycompany
    -0.69
    anovich
    -0.69
    ppuden
    -0.69
    POSITIVE LOGITS
     Raise
    1.65
     raise
    1.63
     raised
    1.59
    Raise
    1.58
     raising
    1.57
    raised
    1.56
     raises
    1.54
     Raising
    1.54
    raise
    1.53
     Raises
    1.50
    Activations Density 0.116%

    No Known Activations