© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to URL encoding and string manipulation in programming

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

    "encode" and related terms

    np_acts-logits-general · gemini-2.0-flash

    encoding URLs and strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Star
    -0.34
     gustan
    -0.34
    Kli
    -0.32
    SpringRunner
    -0.32
     Star
    -0.31
     considerar
    -0.31
    Linq
    -0.31
     ér
    -0.30
    TacToe
    -0.29
    úrese
    -0.28
    POSITIVE LOGITS
     encoding
    2.02
     encode
    2.02
     Encoding
    1.91
    encode
    1.90
     Encode
    1.84
    encoding
    1.80
    Encode
    1.77
     encodes
    1.77
     encoded
    1.73
    Encoding
    1.65
    Activations Density 0.201%

    No Known Activations