© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 754
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or statistics related to economic or quantitative contexts

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

    Follows "is," "which," "suppose," or "this"

    np_acts-logits-general · gemini-2.0-flash

    comparing questions and statements

    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
    rungsseite
    -0.71
    URLException
    -0.63
     estekak
    -0.60
    AddTagHelper
    -0.59
     Autorizaciones
    -0.58
    KommentareTeilen
    -0.56
     kasarigan
    -0.56
     relâche
    -0.54
    Демографія
    -0.54
    tvguidetime
    -0.54
    POSITIVE LOGITS
     numberWith
    0.35
    🏻
    0.35
    habi
    0.34
    '
    0.34
    izzle
    0.32
    éreo
    0.32
     evapor
    0.31
    )));
    0.31
    édi
    0.31
     史
    0.31
    Activations Density 0.486%

    No Known Activations