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. 2870
    Prev
    Next
    INDEX
    Explanations

    statistical data or quantitative information.

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

    information or details related to events, promotions, news, and organizations.

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

    phone numbers, particularly the last few digits of phone numbers.

    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
    ppio
    -0.54
    unsplash
    -0.50
    beitet
    -0.50
    oredCriteria
    -0.49
    interceptors
    -0.48
     Unlimited
    -0.48
    Unlimited
    -0.45
     unlimited
    -0.45
     @
    -0.45
    bitan
    -0.44
    POSITIVE LOGITS
    KommentareTeilen
    0.80
     صوتيه
    0.68
     telefone
    0.61
    Fone
    0.61
     telef
    0.60
    出版年
    0.60
     telephones
    0.59
     telefoon
    0.59
     ILogger
    0.58
    FontOfSize
    0.58
    Activations Density 0.095%

    No Known Activations