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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13669
    Prev
    Next
    INDEX
    Explanations

    references to action or interactions involving people, particularly in contexts of communication and response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.44
    Occasionally
    -0.43
    Slf
    -0.42
    偶尔
    -0.38
    matchCondition
    -0.38
    每一次
    -0.38
    +#+
    -0.37
    AutoScaleMode
    -0.36
     Occasionally
    -0.36
    MemoryWarning
    -0.35
    POSITIVE LOGITS
     immediately
    3.91
    immediately
    3.48
     Immediately
    3.39
     immediate
    3.28
    Immediately
    3.23
     instantly
    3.20
     inmediatamente
    3.02
     imediatamente
    2.95
    immediate
    2.94
     immédiatement
    2.91
    Activations Density 1.613%

    No Known Activations