© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14253
    Prev
    Next
    INDEX
    Explanations

    preferences and actions related to managing content collections

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

    Chinese text and translations

    np_acts-logits-general · gemini-2.0-flash

    media states: watching, watched, unfinished, available

    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
     purpoſe
    -0.66
     ſtate
    -0.62
     ſtre
    -0.60
     houſe
    -0.55
     pleaſure
    -0.55
     uſed
    -0.54
     fubject
    -0.54
     diſt
    -0.52
     paſſ
    -0.52
     ſub
    -0.52
    POSITIVE LOGITS
     незавершена
    0.61
    principalColumn
    0.61
     BoxDecoration
    0.56
    ﹧
    0.56
    tôi
    0.55
     photolibrary
    0.54
    ziasztok
    0.54
    gså
    0.52
    
    0.51
    cửa
    0.50
    Activations Density 0.077%

    No Known Activations