© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 684
    Prev
    Next
    INDEX
    Explanations

    contrastive phrases and qualifiers that indicate skepticism or critique

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

    concessions and contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.56
    Espèce
    -0.40
    省市镇
    -0.39
    bnf
    -0.36
    setof
    -0.35
     Hor
    -0.34
    anguardia
    -0.34
    izop
    -0.34
    UIControlState
    -0.34
    nestjs
    -0.33
    POSITIVE LOGITS
     nonetheless
    0.65
     '\\;'
    0.56
     nevertheless
    0.56
    终究
    0.56
    
    0.52
    Nonetheless
    0.52
     Dennoch
    0.52
    enderror
    0.50
     Nonetheless
    0.50
     AttributeSet
    0.50
    Activations Density 0.072%

    No Known Activations