© 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. 14452
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to emotional depth and vulnerability in photography

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

    preceding pronouns or feeling-related words

    np_acts-logits-general · gemini-2.0-flash

    connected, freedom, how it affects

    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
    最快更新
    -0.66
     apprécié
    -0.66
     vœux
    -0.66
     execução
    -0.66
     assistência
    -0.65
    odly
    -0.65
    targeting
    -0.61
     jugé
    -0.61
     calendriers
    -0.60
     eseguire
    -0.60
    POSITIVE LOGITS
     somehow
    0.67
     Ril
    0.57
    TagMode
    0.54
     daß
    0.53
     Montaigne
    0.52
     teil
    0.52
    Somehow
    0.51
     Ahnung
    0.50
    >//
    0.49
     writer
    0.49
    Activations Density 0.378%

    No Known Activations