© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14609
    Prev
    Next
    INDEX
    Explanations

    content related to biological processes and structures associated with cells and diseases

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

    Follows a noun that is often followed by "called"

    np_acts-logits-general · gemini-2.0-flash

    what is called

    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
    WithIOException
    -0.61
    ंदीखरीदारी
    -0.57
    chaik
    -0.55
    PreAuthorize
    -0.55
    hyrchwyd
    -0.54
    ględ
    -0.53
    KURZBESCHREIBUNG
    -0.51
    mended
    -0.51
    ramentas
    -0.50
     Roskov
    -0.50
    POSITIVE LOGITS
     called
    3.47
    called
    2.84
     Called
    2.62
     CALLED
    2.54
    Called
    2.49
     known
    2.48
     llamado
    2.48
     llamada
    2.35
     termed
    2.23
     chamado
    2.23
    Activations Density 0.975%

    No Known Activations