Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13401
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BoxShadow
    -0.65
    tvguidetime
    -0.57
    achite
    -0.53
     tartalomajánló
    -0.53
    ATTACHMENT
    -0.51
    IntoConstraints
    -0.49
     surla
    -0.49
     Ouro
    -0.49
    academic
    -0.49
    Objective
    -0.48
    POSITIVE LOGITS
     kaynağından
    0.71
    saraba
    0.70
     nahilalakip
    0.66
     ویکی‌پدی
    0.61
    lient
    0.59
    WriteBarrier
    0.57
     समीक्षाओं
    0.55
     '\\;'
    0.55
    cshtml
    0.55
    最快更新
    0.54
    Activations Density 2.025%

    No Known Activations