© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7940
    Prev
    Next
    INDEX
    Explanations

    references to "No" or numerical ratings

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

    "No" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    numbers or "No"

    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
     AssemblyCulture
    -0.67
    astéroïdes
    -0.58
     насељу
    -0.57
    RRect
    -0.55
    XmlEnum
    -0.53
    енча
    -0.52
    RenderAtEndOf
    -0.52
    jsii
    -0.51
    /***/
    -0.50
     Vikipedi
    -0.49
    POSITIVE LOGITS
     longer
    0.78
     Longer
    0.68
    Longer
    0.65
    vartis
    0.62
     matter
    0.61
    veau
    0.60
    tifiable
    0.59
    longer
    0.57
    tifier
    0.54
    ContentAsync
    0.54
    Activations Density 0.098%

    No Known Activations