© 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. 31-GEMMASCOPE-RES-16K
    11. 8487
    Prev
    Next
    INDEX
    Explanations

    elements related to language use and communication, particularly with a focus on expressions of understanding, confusion, and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of informal, conversational language and casual tone markers like punctuation, emoticons, and colloquial expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.64
     defaultstate
    -0.57
    providedIn
    -0.56
    matchCondition
    -0.52
     ligiloj
    -0.48
     TestBed
    -0.47
    HasAnnotation
    -0.45
    InjectAttribute
    -0.44
     BorderSide
    -0.43
    pexpr
    -0.43
    POSITIVE LOGITS
     lol
    2.02
     haha
    1.95
     LOL
    1.82
     hahaha
    1.75
     😂
    1.70
     hehe
    1.66
    lol
    1.60
    😂
    1.59
     hahah
    1.58
     lmao
    1.56
    Activations Density 0.423%

    No Known Activations