© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 15251
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court actions and statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewLabel
    -0.56
    marginRight
    -0.54
    سطس
    -0.53
    och
    -0.49
    первых
    -0.49
     care
    -0.49
    음
    -0.46
    ficit
    -0.46
    hala
    -0.46
    oriam
    -0.46
    POSITIVE LOGITS
    Tikang
    0.87
     endregion
    0.76
    ImageContext
    0.71
    BufferException
    0.71
     morire
    0.70
     appunt
    0.69
    TagMode
    0.69
    stateProvider
    0.68
    AxisAlignment
    0.68
     становника
    0.67
    Activations Density 1.301%

    No Known Activations