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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5669
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements within sentences

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

    "Th" at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    opening quotation marks

    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
     gând
    -0.59
    .
    -0.58
    . 
    -0.57
     démocr
    -0.56
     scolaires
    -0.55
     Савезне
    -0.54
     électroniques
    -0.54
     väli
    -0.53
     enää
    -0.51
     geométrico
    -0.50
    POSITIVE LOGITS
     Th
    1.07
    Th
    0.99
     Tho
    0.92
     Thi
    0.92
     Tha
    0.84
    Tho
    0.83
     Ther
    0.82
    Thi
    0.80
    Tha
    0.78
     Wh
    0.73
    Activations Density 0.203%

    No Known Activations