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. 20-GEMMASCOPE-RES-16K
    6. 8659
    Prev
    Next
    INDEX
    Explanations

    elements related to technical programming logic and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.64
    MLLoader
    -0.58
     cast
    -0.54
    eneuve
    -0.54
    PyExc
    -0.53
    iconque
    -0.52
    égorie
    -0.51
     Roskov
    -0.51
    PrintWriter
    -0.50
    اران
    -0.49
    POSITIVE LOGITS
    Constants
    0.86
     Constants
    0.82
    constants
    0.74
     constants
    0.74
    Const
    0.69
     Const
    0.63
    Constantes
    0.63
    Consts
    0.61
    Config
    0.60
    consts
    0.58
    Activations Density 0.338%

    No Known Activations