Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 115346
    Prev
    Next
    INDEX
    Explanations

    expressions indicating comparison or emphasis, particularly in relation to numbers and quantifiers

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

    whopping amounts and exclamations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     صوتيه
    -0.46
    TagMode
    -0.46
    collo
    -0.39
    Outdoor
    -0.39
    dafx
    -0.37
     boite
    -0.36
    页面存档备份
    -0.36
    Parti
    -0.35
    Thy
    -0.35
    稍
    -0.35
    POSITIVE LOGITS
    なんと
    0.93
     addirittura
    0.80
     sogar
    0.65
     kasarigan
    0.64
     persino
    0.61
     whopping
    0.60
     aż
    0.59
     dokonce
    0.59
    竟
    0.58
     Савезне
    0.57
    Activations Density 0.024%

    No Known Activations