© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8927
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and attitudes

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

    Affirmative responses like "okay" or "fine"

    np_acts-logits-general · gemini-2.0-flash

    okay or fine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    debounce
    -0.46
    tooltip
    -0.45
    ":["
    -0.44
    над
    -0.43
    Хьажоргаш
    -0.42
     Unidas
    -0.42
     gereken
    -0.41
     potenti
    -0.41
    īgs
    -0.41
     lagged
    -0.41
    POSITIVE LOGITS
     okay
    1.53
     OK
    1.50
     ok
    1.41
     alright
    1.30
     OKAY
    1.26
    okay
    1.23
    OK
    1.17
     Ok
    1.16
    Ok
    1.12
    没关系
    1.05
    Activations Density 0.231%

    No Known Activations