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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 609
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to writing skills and media literacy education

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

    discussion of writing and textual analysis, especially the structure, evaluation, and organization of arguments or documents.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    essay writing

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adone
    -0.39
    operability
    -0.38
     Lets
    -0.38
     Oh
    -0.36
     باش
    -0.33
     Presby
    -0.33
    વે
    -0.32
    ichè
    -0.32
     игрушки
    -0.32
     Carlisle
    -0.32
    POSITIVE LOGITS
    TagMode
    0.59
     essay
    0.59
     essays
    0.54
    WebServlet
    0.54
     statement
    0.52
     topic
    0.50
     Glieder
    0.50
    
    0.50
     Statement
    0.49
     rédaction
    0.49
    Activations Density 0.288%

    No Known Activations