© 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. 10875
    Prev
    Next
    INDEX
    Explanations

    details related to chemical structures and compositions

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

    Crystal lattice structures and directions

    np_acts-logits-general · gemini-2.0-flash

    crystal lattice structures and directions

    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
     utafitiHapana
    -0.69
    ScopeManager
    -0.66
    UrlResolution
    -0.63
    fjspx
    -0.62
     mapStateToProps
    -0.59
    writeFieldEnd
    -0.59
    GEBURTSDATUM
    -0.58
    abestanden
    -0.56
     resourceCulture
    -0.55
     intptr
    -0.54
    POSITIVE LOGITS
     crystal
    1.00
     Crystal
    0.88
    crystal
    0.86
    Crystal
    0.82
     crystals
    0.81
     lattice
    0.78
     Crystals
    0.78
     crystalline
    0.73
     Cryst
    0.72
     kristal
    0.72
    Activations Density 1.099%

    No Known Activations