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. 10400
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols in various contexts

    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
    ודם
    -0.46
    ण्ड
    -0.41
    ệt
    -0.41
    ריות
    -0.40
     Such
    -0.40
    ब्द
    -0.39
     olduğ
    -0.39
    ങ്ങൾ
    -0.39
    ומים
    -0.38
    न्स
    -0.36
    POSITIVE LOGITS
     estimés
    0.83
    migrationBuilder
    0.81
     initComponents
    0.80
    tagHelperRunner
    0.79
     Undeclared
    0.67
    httphttps
    0.65
    setVerticalGroup
    0.65
     estekak
    0.64
     reCAPTCHA
    0.63
     CreateTagHelper
    0.62
    Activations Density 0.019%

    No Known Activations