© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 28149
    Prev
    Next
    INDEX
    Explanations

    instances of the word "approximately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nerd
    -0.49
    Nerd
    -0.44
    But
    -0.44
     feroit
    -0.43
    else
    -0.42
     initView
    -0.42
    steering
    -0.42
     verrez
    -0.42
    Portail
    -0.41
     faudra
    -0.40
    POSITIVE LOGITS
     approximately
    2.02
    approximately
    1.77
     Approximately
    1.75
    Approximately
    1.70
     approximate
    1.38
     aproximadamente
    1.30
     approx
    1.28
     Approximate
    1.19
     approxim
    1.18
     roughly
    1.17
    Activations Density 0.017%

    No Known Activations