© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 774
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and related modifiers in legal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.49
     favourites
    -0.38
     gezondheid
    -0.38
     utafitiHapana
    -0.38
    TintMode
    -0.38
     busiest
    -0.37
    Worse
    -0.36
     cheapest
    -0.36
    favourite
    -0.36
    Worst
    -0.35
    POSITIVE LOGITS
     notion
    0.83
     argument
    0.75
     question
    0.71
     discussion
    0.70
     idea
    0.66
     context
    0.65
     concept
    0.63
     emphasis
    0.63
     reader
    0.63
     logic
    0.63
    Activations Density 1.139%

    No Known Activations