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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15624
    Prev
    Next
    INDEX
    Explanations

    numerical references, particularly related to age or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.84
    /
    -0.82
    )
    -0.70
    er
    -0.67
     Orrell
    -0.66
     def
    -0.64
     “
    -0.63
    ly
    -0.63
    ︎
    -0.62
    >
    -0.62
    POSITIVE LOGITS
     eighty
    1.20
     seventy
    1.14
     ninety
    1.12
     sixty
    1.12
     fifty
    1.07
     Theſe
    1.06
     twenty
    1.05
     nineteen
    1.04
     forty
    1.04
     thirty
    1.03
    Activations Density 0.125%

    No Known Activations