© 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. 21-GEMMASCOPE-RES-16K
    11. 2667
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and confrontational sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.92
    XmlAccessType
    -0.70
     HFILL
    -0.67
     utafitiHapana
    -0.67
     disambiguazione
    -0.65
    Cyfeiriadau
    -0.64
    Чыгана
    -0.63
     استنادى
    -0.63
    addCriterion
    -0.62
    thâu
    -0.61
    POSITIVE LOGITS
     took
    0.30
     was
    0.28
     fell
    0.28
     came
    0.28
     illet
    0.27
     saw
    0.26
     inexp
    0.26
     were
    0.26
     gave
    0.26
     cerimonia
    0.25
    Activations Density 0.042%

    No Known Activations