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. 5415
    Prev
    Next
    INDEX
    Explanations

    elements related to procedural or analytical aspects in complex discussions

    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
    ito
    -0.48
    UpInside
    -0.47
    Jegyzetek
    -0.47
     Gedanken
    -0.46
     personally
    -0.46
    self
    -0.43
    IntoConstraints
    -0.42
    тивность
    -0.42
     espoir
    -0.42
     yaşad
    -0.42
    POSITIVE LOGITS
     itself
    0.86
    thâu
    0.84
     autorytatywna
    0.81
     Itself
    0.74
    itself
    0.73
     للاسماء
    0.71
    IonicModule
    0.67
    findpost
    0.65
     DbSet
    0.63
     disambiguazione
    0.61
    Activations Density 0.835%

    No Known Activations