© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3648
    Prev
    Next
    INDEX
    Explanations

    references to applications or products, particularly those associated with technology or patents

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

    Comes before years/dates

    np_acts-logits-general · gemini-2.0-flash

    SIZING TIP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    ↵↵
    -0.58
    <sup>
    -0.57
    <i>
    -0.52
    <u>
    -0.51
    <b>
    -0.51
    <sub>
    -0.51
    <em>
    -0.49
    <strong>
    -0.45
    <code>
    -0.42
    ↵
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.79
     unknownFields
    0.70
    PerformLayout
    0.66
     Bewußt
    0.65
     Roskov
    0.63
     насељу
    0.63
    geführten
    0.61
     wikipagina
    0.60
     otomatig
    0.60
     Geſch
    0.60
    Activations Density 1.248%

    No Known Activations