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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5976
    Prev
    Next
    INDEX
    Explanations

    references to the OpenGL and related graphics libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.95
    Personensuche
    -0.90
    AccessorTable
    -0.89
    adpleegd
    -0.88
     HasFactory
    -0.87
     خارجية
    -0.82
     Púb
    -0.80
    awaiter
    -0.78
    requireNonNull
    -0.78
    FieldBuilder
    -0.77
    POSITIVE LOGITS
     GL
    1.53
     gl
    1.45
     Gl
    1.39
    gl
    1.37
    GL
    1.32
    Gl
    1.25
     GLC
    1.01
     GLS
    1.00
     gle
    0.99
     gla
    0.99
    Activations Density 0.116%

    No Known Activations