© 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 EvalsExportsAPI 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. 10755
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or similar sequences in text

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

    Two- or three-letter words

    np_acts-logits-general · gemini-2.0-flash

    tuning, tropism, tetanic, tensor

    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
    sis
    -0.76
    sor
    -0.76
    queryInterface
    -0.75
    able
    -0.75
    sof
    -0.74
    ه‌اند
    -0.70
    sch
    -0.69
    eral
    -0.68
    ting
    -0.68
    ype
    -0.66
    POSITIVE LOGITS
    Refrain
    0.40
    onAttach
    0.40
    as
    0.39
    arp
    0.38
     StatelessWidget
    0.37
    an
    0.37
     tahu
    0.37
    capsule
    0.36
     recevez
    0.36
     autorytatywna
    0.36
    Activations Density 0.318%

    No Known Activations