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. 8-GEMMASCOPE-RES-16K
    6. 14328
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causality and consequence in processes and events

    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
     rehearing
    -0.75
    BagLayout
    -0.58
     nakalista
    -0.55
     Administrativna
    -0.54
     HttpNotFound
    -0.53
    tvguidetime
    -0.53
    adaptiveStyles
    -0.52
     Survive
    -0.52
     preoperative
    -0.52
     jogging
    -0.51
    POSITIVE LOGITS
     consequently
    0.86
     thereby
    0.85
     resulting
    0.84
    导致
    0.79
     causing
    0.76
     resultant
    0.75
     Consequently
    0.74
    導致
    0.74
     waardoor
    0.73
    resulting
    0.72
    Activations Density 0.608%

    No Known Activations