© 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. 20-GEMMASCOPE-RES-16K
    11. 9058
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     hjelp
    -0.47
     entry
    -0.45
     entrer
    -0.43
     enters
    -0.43
     openings
    -0.41
    Composição
    -0.41
     Initialized
    -0.41
     entries
    -0.41
     UIKit
    -0.40
     tempel
    -0.40
    POSITIVE LOGITS
     probably
    1.11
    probably
    1.05
    Probably
    1.00
     Probably
    0.98
     prolly
    0.85
     likely
    0.82
     wahrscheinlich
    0.79
    bably
    0.77
     probable
    0.75
     probab
    0.75
    Activations Density 0.062%

    No Known Activations