© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3834
    Prev
    Next
    INDEX
    Explanations

    movements or actions involving vertical displacement

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

    Directional movement: up or down

    np_acts-logits-general · gemini-2.0-flash

    up, down, stairs

    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
     Roskov
    -0.55
     crossing
    -0.55
    ropods
    -0.53
    uchungen
    -0.52
     Crossing
    -0.52
     насељу
    -0.52
    Crossing
    -0.52
    auder
    -0.50
    })();
    
    -0.50
    kháu
    -0.49
    POSITIVE LOGITS
     hill
    0.70
    Legături
    0.62
     stairs
    0.62
    ContentAsync
    0.60
    tagext
    0.57
    EndContext
    0.57
    ناة
    0.56
     ranks
    0.55
     виправивши
    0.53
     classement
    0.53
    Activations Density 0.131%

    No Known Activations