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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13485
    Prev
    Next
    INDEX
    Explanations

    references to spatial positions or directions

    oai_token-act-pair · gemini-2.0-flash

    right or left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.67
    orkshire
    -0.61
    }{*}{}
    -0.60
    }],
    
    -0.56
    Autoritní
    -0.56
    Personendaten
    -0.56
    >>>>>>>
    -0.55
    ughty
    -0.55
     VIAF
    -0.54
    addCriterion
    -0.54
    POSITIVE LOGITS
     Juneau
    0.49
     Chwiliwch
    0.49
     canto
    0.49
     rectangle
    0.48
     rectangles
    0.47
    TopLeft
    0.47
     Tetris
    0.47
     PopupWindow
    0.47
    PositiveButton
    0.47
     corners
    0.47
    Activations Density 0.912%

    No Known Activations