© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31533
    Prev
    Next
    INDEX
    Explanations

    function parameters and return type annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    function parameter and return documentation descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.53
    Clik
    -0.43
     groundwork
    -0.41
    รอง
    -0.40
    igshid
    -0.40
    im
    -0.39
    UnknownFields
    -0.39
    رشف
    -0.39
    ima
    -0.38
    MessageTagHelper
    -0.38
    POSITIVE LOGITS
     kasarigan
    0.81
    $_['
    0.70
    <?=
    0.67
     CreateTagHelper
    0.66
    :✨
    0.63
    ustre
    0.61
    SBATCH
    0.61
    ´)
    0.60
    Spoljašnje
    0.60
     NgModule
    0.60
    Activations Density 0.010%

    No Known Activations