© 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. 8096
    Prev
    Next
    INDEX
    Explanations

    specific names of media outlets and publications

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

    Followed by a publication name

    np_acts-logits-general · gemini-2.0-flash

    names of publications or websites

    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
    jsdelivr
    -0.65
    bootstrapcdn
    -0.57
     as
    -0.49
     and
    -0.48
     in
    -0.47
     consistently
    -0.46
     OMITBAD
    -0.45
    houding
    -0.45
    unteers
    -0.45
     signature
    -0.45
    POSITIVE LOGITS
     Anſ
    0.81
    rungsseite
    0.76
    onews
    0.75
    News
    0.74
    NameInMap
    0.74
    ContentAsync
    0.74
    Tembelea
    0.73
    expandindo
    0.73
     חיצוניים
    0.73
     <<<<<<<<<<<<<<
    0.72
    Activations Density 0.227%

    No Known Activations