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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7835
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to background styling

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

    CSS property `background`

    np_acts-logits-general · gemini-2.0-flash

    background styling

    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
     seigneur
    -0.53
     Denkmal
    -0.50
    ampilkan
    -0.49
     AssemblyCulture
    -0.48
    Життєпис
    -0.48
    CppMethod
    -0.47
     cazul
    -0.47
    ALLEN
    -0.46
     fédé
    -0.46
    ocino
    -0.46
    POSITIVE LOGITS
    image
    0.68
     image
    0.67
     noise
    0.65
    repeat
    0.62
     music
    0.62
     Noise
    0.61
    ngdoc
    0.61
     color
    0.60
    color
    0.60
    Repeat
    0.60
    Activations Density 0.086%

    No Known Activations