© 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. 10-GEMMASCOPE-RES-16K
    6. 10465
    Prev
    Next
    INDEX
    Explanations

    references to accountability and consequences for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.78
     pleaſure
    -0.75
     fieldNum
    -0.73
     myſelf
    -0.73
     Monfieur
    -0.72
     Diſ
    -0.72
     houſe
    -0.71
     Theſe
    -0.70
     ſtate
    -0.69
    ContentAsync
    -0.68
    POSITIVE LOGITS
    Vidite
    0.77
     незавершена
    0.73
    KURZBESCHREIBUNG
    0.60
    تقاوى
    0.59
     lack
    0.54
     vì
    0.52
    Geplaatst
    0.49
    StreetMap
    0.49
    因
    0.48
     vermis
    0.46
    Activations Density 0.378%

    No Known Activations