© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and API structure in the text

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

    Code, file paths, or references

    np_acts-logits-general · gemini-2.0-flash

    proto definition or identifier

    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
     Monfieur
    -1.29
     itſelf
    -1.22
     myſelf
    -1.22
     Theſe
    -1.22
     auroit
    -1.21
     feroit
    -1.20
    CloseOperation
    -1.18
     Houſe
    -1.17
    IntoConstraints
    -1.16
     pouvoit
    -1.15
    POSITIVE LOGITS
     
    0.80
     P
    0.74
     T
    0.74
     O
    0.73
     D
    0.72
     M
    0.71
     i
    0.70
     v
    0.69
     e
    0.69
     d
    0.69
    Activations Density 0.060%

    No Known Activations