© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 120370
    Prev
    Next
    INDEX
    Explanations

    terms that denote certainty or inevitability

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

    unavoidable, inevitable, undisputed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rallado
    -0.60
     Biôgrafia
    -0.53
     informée
    -0.51
    ScopeManager
    -0.48
    lámpara
    -0.46
     crónica
    -0.46
     HasFactory
    -0.46
     FetchType
    -0.46
    bildning
    -0.46
    orsch
    -0.45
    POSITIVE LOGITS
     undeniable
    1.70
     unmistakable
    1.23
     indisputable
    1.18
     undeniably
    1.09
     unavoidable
    1.05
     inescapable
    1.00
     unmistak
    0.99
     unquestion
    0.91
     unstoppable
    0.86
     incont
    0.85
    Activations Density 0.006%

    No Known Activations