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. 15468
    Prev
    Next
    INDEX
    Explanations

    characters dealing with personal struggles or transformations within a larger narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    hamcrest
    -0.38
    initComponents
    -0.36
    ContentAsync
    -0.34
    lblNewLabel
    -0.34
     unis
    -0.34
     Lino
    -0.34
    LayoutPanel
    -0.34
    cayaan
    -0.33
    Portale
    -0.33
     réunis
    -0.33
    POSITIVE LOGITS
     accident
    0.52
    Попис
    0.51
    accident
    0.51
     accidentally
    0.50
     accidente
    0.45
     prieš
    0.45
     escaped
    0.44
     accidental
    0.43
    falling
    0.43
    cocc
    0.43
    Activations Density 0.345%

    No Known Activations