© 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. 24-GEMMASCOPE-RES-16K
    6. 9210
    Prev
    Next
    INDEX
    Explanations

    occurrences of code import statements and annotations

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

    Tokens after "@" or "/"

    np_acts-logits-general · gemini-2.0-flash

    @ or [ followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.56
     mukaan
    -0.53
     figlia
    -0.48
     prieš
    -0.48
     înainte
    -0.45
     físico
    -0.45
     illustrationer
    -0.44
     independientes
    -0.44
    hbase
    -0.43
    Standort
    -0.43
    POSITIVE LOGITS
    ########.
    0.89
    AddTagHelper
    0.71
     فريبيس
    0.70
    ंदीखरीदारी
    0.70
    MemoryWarning
    0.70
    دانشنامهٔ
    0.68
     EconPapers
    0.68
    tagHelperRunner
    0.68
     kasarigan
    0.67
     estekak
    0.67
    Activations Density 0.097%

    No Known Activations