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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1831
    Prev
    Next
    INDEX
    Explanations

    themes of reconciliation and personal struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.76
    StoryboardSegue
    -0.74
     дописавши
    -0.72
    цездатний
    -0.72
    TintMode
    -0.72
     ſeveral
    -0.69
    drawSprites
    -0.69
     pleaſure
    -0.68
     geox
    -0.66
     themſelves
    -0.65
    POSITIVE LOGITS
    帖最后由
    0.55
    Inhalt
    0.51
     trib
    0.49
    vinger
    0.48
     topics
    0.47
    Joh
    0.47
     capo
    0.47
     personal
    0.47
     narrator
    0.47
     adresu
    0.47
    Activations Density 0.058%

    No Known Activations