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. 11846
    Prev
    Next
    INDEX
    Explanations

    technical terminology and phrases related to genetic and biochemical research

    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
    CodedInputStream
    -0.78
    DockStyle
    -0.77
    ✨:
    -0.74
     informée
    -0.72
    StandardCharsets
    -0.71
     AllMovie
    -0.68
    hasMoreElements
    -0.66
     Baillargeon
    -0.66
    endregion
    -0.65
    principalColumn
    -0.64
    POSITIVE LOGITS
    pyx
    4.18
    Pyx
    1.74
     <<<<<<<<<<<<<<
    0.78
     CYTHON
    0.75
    PYX
    0.74
    tagHelper
    0.72
    scriptcase
    0.67
    jspx
    0.66
     PyObject
    0.63
    حياته
    0.62
    Activations Density 0.014%

    No Known Activations