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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36617
    Prev
    Next
    INDEX
    Explanations

    themes of struggle and perseverance in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     divertimento
    -0.59
     ambientale
    -0.56
     besides
    -0.54
     morire
    -0.54
    GOTREF
    -0.52
     événements
    -0.51
     célèbres
    -0.51
     gants
    -0.50
    WriteBarrier
    -0.50
     miniatura
    -0.50
    POSITIVE LOGITS
    IsContent
    0.85
    AnchorStyles
    0.79
    Билгалдахарш
    0.73
    HostException
    0.69
     GenerationType
    0.68
     Lightboxes
    0.67
     مشين
    0.65
    DockStyle
    0.65
    WritableDatabase
    0.64
    yntaxException
    0.63
    Activations Density 0.061%

    No Known Activations