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. 3111
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming, management, and system architecture

    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
     виправивши
    -0.57
    примеча
    -0.56
    WillAppear
    -0.56
    脚注の使い方
    -0.55
    lidene
    -0.54
    chette
    -0.54
    ktop
    -0.51
     Vikipedi
    -0.50
    fetchone
    -0.50
     forState
    -0.50
    POSITIVE LOGITS
     coordinating
    0.63
     organizing
    0.63
     presiding
    0.62
     koordin
    0.61
     przewod
    0.59
     rassemb
    0.59
     comanda
    0.57
     orchestr
    0.56
     anfitrión
    0.56
     organizador
    0.56
    Activations Density 0.702%

    No Known Activations