© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    points related to computational systems and methodologies for data processing

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

    "Into" followed by articles or numbers

    np_acts-logits-general · gemini-2.0-flash

    dividing into multiple parts

    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
    цездатний
    -0.60
     '\\;'
    -0.59
    Neither
    -0.56
    后者
    -0.55
     ejemplos
    -0.54
     ultimi
    -0.51
     berdua
    -0.51
     engraçadas
    -0.51
     letz
    -0.50
     exemplos
    -0.49
    POSITIVE LOGITS
     separate
    1.31
     multiple
    1.23
     different
    1.09
     distinct
    1.04
     seperate
    1.04
     individual
    1.03
     several
    1.03
    separate
    1.03
     interrelated
    1.01
     overlapping
    1.01
    Activations Density 0.990%

    No Known Activations