© 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. 22-GEMMASCOPE-RES-16K
    11. 16355
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluations of emotional states or wellbeing

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

    preceding adverbs of degree

    np_acts-logits-general · gemini-2.0-flash

    degree of intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.50
    tető
    -0.49
     meilleures
    -0.49
    istible
    -0.49
    lepší
    -0.48
    Przypisy
    -0.48
    ̣i
    -0.47
     varsa
    -0.47
     meilleurs
    -0.47
    IfNeeded
    -0.46
    POSITIVE LOGITS
     quite
    2.75
     very
    2.74
    quite
    2.38
    very
    2.21
     Quite
    2.19
    Quite
    2.14
    Very
    2.12
     fairly
    2.09
     extremely
    2.08
     VERY
    2.08
    Activations Density 0.733%

    No Known Activations