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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3554
    Prev
    Next
    INDEX
    Explanations

    the term "much" and its variants to indicate a significant quantity or importance

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

    "Much" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    much of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DRS
    -0.50
    HLA
    -0.49
     Lauder
    -0.48
    oflavin
    -0.47
     kierow
    -0.46
     laure
    -0.46
    løs
    -0.46
     Naidu
    -0.44
    ais
    -0.43
    Datuak
    -0.42
    POSITIVE LOGITS
     MUCH
    0.93
     much
    0.93
    much
    0.85
    Much
    0.84
     Much
    0.84
     more
    0.75
     mucho
    0.72
    Viel
    0.64
     little
    0.63
     viel
    0.63
    Activations Density 0.071%

    No Known Activations