© 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. 18-GEMMASCOPE-RES-16K
    11. 15139
    Prev
    Next
    INDEX
    Explanations

    keywords related to character interactions and transitions in gaming or storytelling

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

    followed by prepositions or commas

    np_acts-logits-general · gemini-2.0-flash

    improve service or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.58
     JpaRepository
    -0.54
    ással
    -0.54
     SwitchCompat
    -0.51
    EnableWeb
    -0.51
     hace
    -0.51
    IVEREF
    -0.51
    horesis
    -0.50
    terdam
    -0.50
    brtc
    -0.49
    POSITIVE LOGITS
     faster
    0.93
     quicker
    0.90
     ולה
    0.90
    脚注の使い方
    0.88
     easier
    0.86
    faster
    0.86
     efficiently
    0.83
     efficacement
    0.79
     better
    0.77
     safely
    0.72
    Activations Density 0.824%

    No Known Activations