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. 12-GEMMASCOPE-RES-16K
    6. 6043
    Prev
    Next
    INDEX
    Explanations

    specific nouns and entities related to different contexts, including health, food, law, and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.50
     مسلم
    -0.48
    ceğ
    -0.48
     displacement
    -0.48
    MessageDigest
    -0.47
    ρός
    -0.43
     divisão
    -0.43
     profiling
    -0.43
     دون
    -0.42
     giusta
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.85
     виправивши
    0.85
    AndEndTag
    0.84
     jsPsych
    0.81
     ddelweddau
    0.78
    хьтан
    0.78
    rrggbb
    0.71
    LookAnd
    0.70
     gynhyrchwyd
    0.68
     للاسماء
    0.68
    Activations Density 0.478%

    No Known Activations