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. 24-GEMMASCOPE-RES-16K
    6. 8033
    Prev
    Next
    INDEX
    Explanations

    data related to financial metrics and production statistics of a company

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

    Companies involved in exploration, resources, or clinical programs

    np_acts-logits-general · gemini-2.0-flash

    junior resource stocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.69
    はじめに
    -0.64
     CreateTagHelper
    -0.61
    Demografia
    -0.58
     '\\;'
    -0.56
    posób
    -0.55
    RenderAtEndOf
    -0.54
    ThroughAttribute
    -0.53
     GenerationType
    -0.51
    αιν
    -0.50
    POSITIVE LOGITS
     exploration
    0.78
     drill
    0.69
     Exploration
    0.68
     explorer
    0.63
     tenements
    0.63
     junior
    0.62
     drilling
    0.62
     explorers
    0.61
    Exploration
    0.61
     juniors
    0.60
    Activations Density 0.111%

    No Known Activations