Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12566
    Prev
    Next
    INDEX
    Explanations

    specific dates or mentions of months within a text

    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
     servici
    -0.54
    xAxis
    -0.54
     has
    -0.52
    rsiniz
    -0.51
     ProtoMessage
    -0.51
    Gale
    -0.51
     Landes
    -0.50
     bas
    -0.49
    Moss
    -0.49
    ../../
    -0.48
    POSITIVE LOGITS
    Clik
    0.89
     betweenstory
    0.84
    SBATCH
    0.75
     елның
    0.72
     Phry
    0.72
    CloseOperation
    0.68
     وتسجيلات
    0.65
     Etrus
    0.64
     ahol
    0.64
     Réponses
    0.64
    Activations Density 0.068%

    No Known Activations