© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4785
    Prev
    Next
    INDEX
    Explanations

    uncertainty or doubt in personal beliefs and opinions

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

    phrases expressing certainty or confidence.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    expressions of epistemic stance—especially first-person assertions of certainty, belief, or doubt about what is or will be the case.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases expressing certainty or strong belief, particularly those beginning with "I'm sure" or "I'm certain."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Personendaten
    -0.55
    oredCriteria
    -0.49
    Autoritní
    -0.48
     ISNI
    -0.46
     autorytatywna
    -0.46
    miento
    -0.46
     voici
    -0.45
    
    -0.45
     betweenstory
    -0.45
     houſe
    -0.44
    POSITIVE LOGITS
     probably
    0.82
    probably
    0.70
    Probably
    0.70
     Probably
    0.68
     prolly
    0.62
     likely
    0.58
    няка
    0.58
     probablemente
    0.57
     doubtless
    0.56
    おそらく
    0.55
    Activations Density 0.282%

    No Known Activations