© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 372
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty and necessity regarding legal obligations or statements

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

    Sentences expressing certainty or inevitability

    np_acts-logits-general · gemini-2.0-flash

    indisputable facts not up for debate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plateado
    -0.44
     cromado
    -0.42
    StatusOK
    -0.41
    NameInMap
    -0.37
    Distribuzione
    -0.37
     lenker
    -0.36
    indépendance
    -0.36
    Distribución
    -0.35
    pakking
    -0.35
     independence
    -0.34
    POSITIVE LOGITS
     inevitable
    0.68
     undeniable
    0.63
     indisputable
    0.60
     inevit
    0.60
     unavoidable
    0.57
     inevitably
    0.55
    必然
    0.54
    ConstraintMaker
    0.54
     unequivocal
    0.54
     undeniably
    0.53
    Activations Density 0.551%

    No Known Activations