© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10823
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the start or initiation of actions or processes

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

    Followed by a verb in "-ing" form

    np_acts-logits-general · gemini-2.0-flash

    beginning of actions

    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
     continued
    -0.75
     continuare
    -0.75
    continuing
    -0.69
     continuance
    -0.69
     blijven
    -0.69
     continuing
    -0.67
     continue
    -0.67
     fortsatt
    -0.65
    haway
    -0.65
    continued
    -0.65
    POSITIVE LOGITS
     anew
    0.78
     preparations
    0.76
     afresh
    0.72
     proceedings
    0.61
     negotiations
    0.60
     earnest
    0.60
     construction
    0.60
     operations
    0.59
    ต้น
    0.58
     discussions
    0.58
    Activations Density 0.135%

    No Known Activations