© 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. 133
    Prev
    Next
    INDEX
    Explanations

    phrases related to bubbles and their various forms or contexts

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

    bubble and related concepts

    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
    ngrx
    -0.51
    GIVEREF
    -0.49
     prêtres
    -0.44
    enterOuterAlt
    -0.42
     Picchu
    -0.40
     hierro
    -0.39
     depreciation
    -0.38
     leña
    -0.38
     distancias
    -0.38
    foglal
    -0.38
    POSITIVE LOGITS
     bubble
    1.85
     Bubble
    1.68
     bubbles
    1.67
    Bubble
    1.65
    bubble
    1.65
     Bubbles
    1.46
    bubbles
    1.46
     BUB
    1.43
    Bubbles
    1.34
     burbuja
    1.33
    Activations Density 0.019%

    No Known Activations