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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7661
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to UTF-8 text encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.66
    +#+#
    -0.60
     وتسجيلات
    -0.55
    niſſe
    -0.55
     Efq
    -0.54
    WithIOException
    -0.54
    :✨
    -0.53
     Monfieur
    -0.52
    lihood
    -0.51
    iſchen
    -0.51
    POSITIVE LOGITS
     utf
    1.05
    UTF
    0.97
     UTF
    0.97
    utf
    0.94
     charset
    0.89
    StandardCharsets
    0.84
    charset
    0.72
    Utf
    0.68
    Charsets
    0.65
    Charset
    0.57
    Activations Density 0.159%

    No Known Activations