© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3886
    Prev
    Next
    INDEX
    Explanations

    architectural features and details related to buildings

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

    Followed by materials (bronze, lead)

    np_acts-logits-general · gemini-2.0-flash

    communist threat or architectural elements

    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
    évaluateur
    -0.70
     intptr
    -0.60
    UserScript
    -0.53
    shard
    -0.52
    EndInit
    -0.52
     varm
    -0.51
    AutoScale
    -0.51
    orghini
    -0.50
    GOTREF
    -0.50
    httphttps
    -0.50
    POSITIVE LOGITS
    енча
    0.66
    __':
    0.59
     interrupted
    0.56
     flanking
    0.55
     capitals
    0.53
     semicirc
    0.52
    wickshire
    0.52
    diensten
    0.50
     дори
    0.50
     pila
    0.50
    Activations Density 0.112%

    No Known Activations