© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    concepts related to pressure and structural integrity in mechanical systems

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

    Tokens preceding causes or results

    np_acts-logits-general · gemini-2.0-flash

    problems and shortcomings

    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
     autorytatywna
    -0.79
    Demografía
    -0.64
    хьтан
    -0.64
    就好了
    -0.62
    matorium
    -0.58
    tagext
    -0.57
     :)</
    -0.57
     :)
    -0.57
     :-)
    -0.55
    いれば
    -0.54
    POSITIVE LOGITS
     causing
    1.74
    causing
    1.48
     resulting
    1.41
    resulting
    1.34
     forcing
    1.33
     causando
    1.29
     mengakibatkan
    1.27
    導致
    1.26
    导致
    1.26
     leading
    1.24
    Activations Density 1.047%

    No Known Activations