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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16120
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of ongoing struggle or challenge

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

    "long way," "long shot," or "by far."

    np_acts-logits-general · gemini-2.0-flash

    by far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    endphp
    -0.69
    Jeografia
    -0.57
     wireType
    -0.55
    äiv
    -0.50
    oden
    -0.49
    graphicx
    -0.48
     iNdEx
    -0.48
     GRAHAM
    -0.47
    łaj
    -0.45
    scryfall
    -0.44
    POSITIVE LOGITS
     far
    1.78
    far
    1.50
     jauh
    1.41
     långt
    1.37
     lejos
    1.33
     langt
    1.32
     FAR
    1.32
    Far
    1.32
     miles
    1.31
     Far
    1.25
    Activations Density 0.173%

    No Known Activations