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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7819
    Prev
    Next
    INDEX
    Explanations

    relative pronouns or adverbs such as "whereby", "which", and "where"

    oai_token-act-pair · gemini-2.0-flash

    whereby/which

    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
    ::_('
    -0.81
    ThroughAttribute
    -0.75
     Bioaccumulative
    -0.66
    addPreferredGap
    -0.66
     ―――
    -0.66
    XmlAccessorType
    -0.65
     RIPRODUZIONE
    -0.65
     vägen
    -0.64
     setw
    -0.64
    RefNanny
    -0.64
    POSITIVE LOGITS
    <bos>
    0.78
     where
    0.66
     gi
    0.52
     when
    0.50
    where
    0.50
    The
    0.46
     
    0.46
     The
    0.45
     c
    0.45
    from
    0.44
    Activations Density 2.537%

    No Known Activations