Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9129
    Prev
    Next
    INDEX
    Explanations

    strong emphasis on specific numerical values or measurements.

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

    details and mentions of health-related topics and medical conditions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    horizontal lines or dividers in text, typically represented by repeated underscores or dashes.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.80
    SharedDtor
    -0.76
    rungsseite
    -0.68
     تانيه
    -0.66
     SEDS
    -0.65
     nonatomic
    -0.64
    ########.
    -0.62
     CUT
    -0.61
    stdc
    -0.61
    ))^{
    -0.60
    POSITIVE LOGITS
    ________________
    0.98
    __
    0.87
    ___
    0.74
    ____
    0.71
    ______
    0.70
    _______
    0.67
    _________
    0.67
    _
    0.66
    __________
    0.66
    ________
    0.65
    Activations Density 0.104%

    No Known Activations