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. 25-GEMMASCOPE-RES-16K
    6. 7943
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and their implications

    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
     Efq
    -0.65
     Púb
    -0.59
     automatiques
    -0.57
    Isolate
    -0.56
     Mandate
    -0.56
     Promise
    -0.55
     Reserve
    -0.55
     greateſt
    -0.54
     spécifiques
    -0.54
     Analyse
    -0.53
    POSITIVE LOGITS
    AndEndTag
    0.78
     CreateTagHelper
    0.71
     AssemblyCulture
    0.70
    +#+#
    0.69
    InSection
    0.69
     MenuView
    0.64
    rrggbb
    0.63
    Being
    0.62
     invokingState
    0.61
    WebServlet
    0.60
    Activations Density 0.334%

    No Known Activations