© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic and decorative qualities

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

    Followed by "add" or related terms

    np_acts-logits-general · gemini-2.0-flash

    adding

    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
     iné
    -0.55
    regard
    -0.47
    gste
    -0.47
    ferrer
    -0.45
    ลัง
    -0.45
    而去
    -0.44
    Expect
    -0.44
     müm
    -0.43
     compren
    -0.43
    lably
    -0.43
    POSITIVE LOGITS
     adds
    1.38
     add
    1.36
     adding
    1.28
     Adds
    1.22
     Adding
    1.14
    adds
    1.14
    Adding
    1.10
     enliven
    1.09
    Adds
    1.09
    增添
    1.05
    Activations Density 0.288%

    No Known Activations