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. 14-GEMMASCOPE-RES-16K
    6. 104
    Prev
    Next
    INDEX
    Explanations

    negative conjunctions and refusals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    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
    -0.69
     fubject
    -0.68
    الإنجليزية
    -0.68
     Bucky
    -0.64
     occaf
    -0.64
     firſt
    -0.63
     onely
    -0.62
     juſt
    -0.61
    LLocation
    -0.61
     propOrder
    -0.61
    POSITIVE LOGITS
     nor
    0.95
    Nor
    0.87
    nor
    0.83
     Nor
    0.83
     any
    0.79
     siquiera
    0.75
     even
    0.71
     anything
    0.70
    StoryboardSegue
    0.70
     MotionEvent
    0.69
    Activations Density 0.146%

    No Known Activations