© 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. 3-GEMMASCOPE-RES-16K
    6. 893
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions related to data analysis and modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.74
     &
    -0.73
    <eos>
    -0.63
    “
    -0.62
    ”
    -0.62
     “
    -0.60
    y
    -0.60
    ly
    -0.59
     same
    -0.57
     
    -0.57
    POSITIVE LOGITS
     CreateTagHelper
    1.09
    :✨
    1.03
    rawDesc
    0.97
     myſelf
    0.97
     calendriers
    0.94
    afficheront
    0.94
    verwijspagina
    0.93
     bağlantılar
    0.92
    )++;
    0.89
     становника
    0.89
    Activations Density 0.357%

    No Known Activations