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. 3436
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or organizations in legal 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
    ंदीखरीदारी
    -0.82
    ########.
    -0.72
    تقاوى
    -0.71
     utafitiHapana
    -0.71
     kaarangay
    -0.70
     مشين
    -0.69
    Geplaatst
    -0.68
    UserScript
    -0.67
    脚注の使い方
    -0.61
     CURIAM
    -0.61
    POSITIVE LOGITS
    ingale
    0.48
    deno
    0.46
     internationaux
    0.42
     ஒரு
    0.41
     Franca
    0.40
     pricing
    0.39
    aarrggbb
    0.39
    AndPassword
    0.39
     particulières
    0.38
    AndEndTag
    0.37
    Activations Density 0.420%

    No Known Activations