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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    expressions of sadness and negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متحده
    -0.64
     fieldNum
    -0.57
    يميديا
    -0.55
    FieldBuilder
    -0.54
     BoxDecoration
    -0.54
     ComVisible
    -0.54
    matchCondition
    -0.52
     StringTokenizer
    -0.51
    featureID
    -0.51
     мәкал
    -0.50
    POSITIVE LOGITS
    EndContext
    0.52
     pitiful
    0.48
    omic
    0.48
     sad
    0.47
    SAD
    0.47
     ModelExpression
    0.45
     Sad
    0.44
    Sad
    0.44
    sad
    0.43
     😢
    0.43
    Activations Density 0.201%

    No Known Activations