© 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-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4939
    Prev
    Next
    INDEX
    Explanations

    various forms of debate and discussion surrounding political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pruch
    -0.40
    Étymologie
    -0.35
     writeTo
    -0.35
    tymologie
    -0.34
    ActionMode
    -0.34
    InputBorder
    -0.33
     Flü
    -0.32
    ᶦ
    -0.32
    strlen
    -0.32
    ⟭
    -0.32
    POSITIVE LOGITS
     issues
    3.05
     issue
    3.02
    issues
    2.64
    issue
    2.61
     Issues
    2.59
    Issues
    2.52
     Issue
    2.44
     ISSUES
    2.38
    Issue
    2.34
     ISSUE
    2.30
    Activations Density 1.303%

    No Known Activations