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. 5967
    Prev
    Next
    INDEX
    Explanations

    specific formatting and structural elements in programming or markup languages

    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
     CreateTagHelper
    -0.69
     يتيمه
    -0.69
     jsPsych
    -0.62
     useAppContext
    -0.59
     Akismet
    -0.59
     onCancelled
    -0.55
     diretta
    -0.51
     diretto
    -0.51
    Климат
    -0.50
     transfieras
    -0.49
    POSITIVE LOGITS
    σμο
    0.57
    +#+
    0.51
     مشين
    0.49
    Nuke
    0.46
    chesse
    0.46
     monst
    0.46
     undead
    0.46
     Undead
    0.45
    unlink
    0.45
    nitus
    0.44
    Activations Density 0.448%

    No Known Activations