© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7671
    Prev
    Next
    INDEX
    Explanations

    phrases and context related to personal experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.63
    latter
    -0.60
    StoryboardSegue
    -0.59
    TableAdapter
    -0.57
    onCreate
    -0.55
    /******/
    -0.54
    ună
    -0.54
    InjectAttribute
    -0.53
    ところです
    -0.52
     your
    -0.52
    POSITIVE LOGITS
     kepad
    0.83
     μαζί
    0.82
     tome
    0.65
     conmigo
    0.61
     comigo
    0.58
     vnto
    0.57
     contigo
    0.57
    IndentedString
    0.57
     ddelweddau
    0.57
     إلي
    0.56
    Activations Density 0.227%

    No Known Activations