© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    references to social gatherings and competitive events involving food and drink

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

    Things enjoyed or done in a location

    np_acts-logits-general · gemini-2.0-flash

    amidst or surrounded by

    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
    دانشنامهٔ
    -0.69
    υχ
    -0.57
    testens
    -0.54
    どうしても
    -0.54
    Viitteet
    -0.53
     fich
    -0.52
    utable
    -0.52
     déjà
    -0.51
    ειν
    -0.51
     cohomology
    -0.51
    POSITIVE LOGITS
     while
    1.19
     sambil
    1.10
     amidst
    1.07
     whilst
    1.02
     surrounded
    0.97
     amid
    0.93
    while
    0.92
     terwijl
    0.92
     accompanied
    0.91
     using
    0.89
    Activations Density 0.536%

    No Known Activations