© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, names, and events related to political and financial contexts

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

    Dates (month name)

    np_acts-logits-general · gemini-2.0-flash

    months followed by hyphens

    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
    tvguidetime
    -0.78
    .",
    -0.76
     Infórmanos
    -0.76
     незавершена
    -0.73
     Geſch
    -0.73
    .";
    -0.73
    httphttps
    -0.70
     kasarigan
    -0.69
     deſſen
    -0.69
    __(/*!
    -0.69
    POSITIVE LOGITS
    :
    0.52
     –
    0.43
     -
    0.40
    ,
    0.37
     :
    0.35
     &
    0.35
    enderror
    0.34
    )
    0.34
     (
    0.32
     =
    0.30
    Activations Density 0.506%

    No Known Activations