© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6651
    Prev
    Next
    INDEX
    Explanations

    words related to development and improvement within various contexts, particularly business and community growth

    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
    ctx
    -0.50
    ouds
    -0.49
     ctx
    -0.46
    으면
    -0.46
    jalna
    -0.45
    理工
    -0.45
    bParam
    -0.45
     demanding
    -0.44
    PostInfinity
    -0.43
    nloa
    -0.43
    POSITIVE LOGITS
     Мексичка
    0.72
     AssemblyCompany
    0.66
    TagMode
    0.64
    StoryboardSegue
    0.63
     daardoor
    0.63
    windowFixed
    0.61
     becauſe
    0.60
     dadurch
    0.60
     Efq
    0.58
    ſelves
    0.58
    Activations Density 0.957%

    No Known Activations