© 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. 6569
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement and affirmation

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

    Follows punctuation or start of turn

    np_acts-logits-general · gemini-2.0-flash

    affirmation and agreement

    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
     ſta
    -0.71
     itſelf
    -0.68
     poffible
    -0.65
     ſch
    -0.64
     ſche
    -0.63
     ſind
    -0.61
     ſte
    -0.61
     ſtand
    -0.60
     myſelf
    -0.59
     ModelExpression
    -0.58
    POSITIVE LOGITS
    GEBURTSDATUM
    0.44
    løs
    0.34
     vraie
    0.33
    īgs
    0.32
     hermano
    0.32
     cristianos
    0.32
     irmão
    0.31
     hyvä
    0.31
     tolle
    0.31
     ampliamente
    0.31
    Activations Density 0.277%

    No Known Activations