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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10606
    Prev
    Next
    INDEX
    Explanations

    various numerical data and identifiers, indicating a focus on technical or scientific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.74
    tagHelperRunner
    -0.72
     дописавши
    -0.71
    ")));
    -0.68
    '):
    -0.66
    )";
    -0.66
    AddTagHelper
    -0.66
    cshtml
    -0.65
    "):
    -0.64
    RegressionTest
    -0.64
    POSITIVE LOGITS
     uſed
    0.72
     poffe
    0.64
     ſmall
    0.63
     préférable
    0.62
     LEYENDO
    0.62
     potest
    0.62
     ſte
    0.60
     Monfieur
    0.58
     ſta
    0.58
     raiſ
    0.57
    Activations Density 1.478%

    No Known Activations