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. 25-GEMMASCOPE-RES-16K
    6. 10243
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research methodologies or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.60
    Extinguishing
    -0.59
    refour
    -0.55
    ifoli
    -0.54
     Wikimedijinoj
    -0.54
    errHandler
    -0.53
    fycat
    -0.52
    šanai
    -0.51
    PreInfinity
    -0.51
     ANCHE
    -0.50
    POSITIVE LOGITS
     which
    4.18
    which
    3.21
     WHICH
    2.81
     Which
    2.73
    Which
    2.64
     laquelle
    2.02
    hich
    1.94
     lequel
    1.91
     wich
    1.86
     whiche
    1.85
    Activations Density 1.850%

    No Known Activations