© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12026
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "write."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.69
     муніципалі
    -0.59
    ramentas
    -0.58
    favicon
    -0.57
    PathVariable
    -0.57
     Relatives
    -0.57
    #+#
    -0.56
     onCreateView
    -0.56
    bundes
    -0.56
     noqa
    -0.55
    POSITIVE LOGITS
     writing
    1.51
     write
    1.49
     Writing
    1.39
    Writing
    1.34
     wrote
    1.32
     Write
    1.30
    write
    1.30
     WRITING
    1.29
    writing
    1.27
     Writes
    1.26
    Activations Density 0.198%

    No Known Activations