© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2148
    Prev
    Next
    INDEX
    Explanations

    terms related to encoding and decoding processes in programming or data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Viel
    -0.50
     rou
    -0.48
     Mather
    -0.47
    庵
    -0.46
    ibid
    -0.45
    pdf
    -0.45
     devoir
    -0.45
    “……”
    -0.44
    增
    -0.44
    象
    -0.43
    POSITIVE LOGITS
     encoded
    1.74
     encode
    1.71
     coded
    1.61
    coded
    1.51
     encodes
    1.51
    encode
    1.49
    encoded
    1.49
     code
    1.41
     encoding
    1.39
     Encode
    1.37
    Activations Density 0.113%

    No Known Activations