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. 13648
    Prev
    Next
    INDEX
    Explanations

    conjunctions and pronouns, but it seems to be highly sensitive to the exact case, potentially identifying sentence structure

    oai_token-act-pair · gemini-2.0-flash

    German and math texts

    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
     a
    -0.62
    انيف
    -0.54
    }")]
    -0.54
    =?";
    -0.54
    updateOne
    -0.54
    stdafx
    -0.54
    NameInMap
    -0.51
    ものです
    -0.48
     one
    -0.48
    还不是
    -0.48
    POSITIVE LOGITS
    脚注の使い方
    0.75
    ArgsConstructor
    0.72
     /\.(
    0.66
    SequentialGroup
    0.63
     /\.
    0.62
    ChromeDriver
    0.61
    DebuggerStep
    0.59
     FileReader
    0.58
    новниш
    0.57
    PropertyChanging
    0.56
    Activations Density 1.594%

    No Known Activations