© 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. 5097
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to physical spaces and their features

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

    after numbers related to buildings

    np_acts-logits-general · gemini-2.0-flash

    architectural descriptions

    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
     kasarigan
    -0.67
    Revenir
    -0.56
     صوتيه
    -0.55
    Sortie
    -0.54
    Datuak
    -0.52
    tigt
    -0.50
     traduit
    -0.50
     bero
    -0.49
     legais
    -0.49
     sanitarios
    -0.48
    POSITIVE LOGITS
    abestanden
    0.63
     unknownFields
    0.57
    ProcessEvent
    0.56
     tartalomajánló
    0.55
    thâu
    0.55
     conservatory
    0.53
     NSCoder
    0.53
     orang
    0.52
    षण
    0.52
     bezeichneter
    0.51
    Activations Density 0.052%

    No Known Activations