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. 2097
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminology related to proofs and formulations

    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
     تضيفلها
    -0.85
    tagHelperRunner
    -0.83
    +#+#
    -0.81
    addPreferredGap
    -0.77
    istoitu
    -0.76
    ValueStyle
    -0.75
    PyExc
    -0.70
    parsedMessage
    -0.69
    qrstuvwxyz
    -0.68
    Biblia
    -0.68
    POSITIVE LOGITS
     confiable
    0.40
     operações
    0.39
     estadía
    0.39
     acá
    0.36
     pienso
    0.35
     gastronomía
    0.35
     perdón
    0.35
     différente
    0.35
     tudom
    0.34
    retanto
    0.34
    Activations Density 4.895%

    No Known Activations