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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15620
    Prev
    Next
    INDEX
    Explanations

    references to personal responsibility and actions

    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
    expandindo
    -0.85
    Datuak
    -0.78
    Diwedd
    -0.73
    FormTagHelper
    -0.72
     AssemblyTitle
    -0.67
     createSprite
    -0.62
    BeginContext
    -0.61
    帖最后由
    -0.61
    InlineData
    -0.61
     KeyError
    -0.56
    POSITIVE LOGITS
     what
    0.93
     What
    0.82
    What
    0.81
    what
    0.77
     hvad
    0.76
     hva
    0.73
     WHAT
    0.68
    évaluateur
    0.67
    WHAT
    0.66
    whats
    0.65
    Activations Density 0.140%

    No Known Activations