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. 12-GEMMASCOPE-RES-16K
    6. 1237
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their operations

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    <eos>
    -0.36
    endswith
    -0.36
     b
    -0.35
    #{
    -0.34
    Privat
    -0.34
     вовсе
    -0.34
    假
    -0.33
     broche
    -0.33
     im
    -0.33
     medio
    -0.33
    POSITIVE LOGITS
    CloseOperation
    0.98
    ConstraintMaker
    0.89
    AccessorTable
    0.89
    AndroidJUnit
    0.88
    DeleteBehavior
    0.88
     useAppContext
    0.87
    sizeCache
    0.86
    __*/
    0.83
    GraphicsUnit
    0.82
     CommonModule
    0.81
    Activations Density 0.200%

    No Known Activations