© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 1114
    Prev
    Next
    INDEX
    Explanations

    contributions to a specific argument or claim regarding a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.64
     betweenstory
    -0.61
     geslacht
    -0.58
    GetAxis
    -0.54
     and
    -0.52
    localctx
    -0.49
     douceur
    -0.48
     الدولى
    -0.48
    enna
    -0.47
    joba
    -0.46
    POSITIVE LOGITS
     EnglishChoose
    0.63
    Datuak
    0.60
     consequently
    0.58
     незавершена
    0.57
    )_/¯
    0.56
    ernalia
    0.56
    migrationBuilder
    0.56
    />";
    0.55
    rasi
    0.55
     дописавши
    0.54
    Activations Density 0.726%

    No Known Activations