Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14669
    Prev
    Next
    INDEX
    Explanations

    references to digital content and images related to maps and locations

    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
    atguigu
    -0.77
    interopRequire
    -0.57
    parsedMessage
    -0.57
    LookAnd
    -0.56
     Normdatei
    -0.52
    openConnection
    -0.52
    UnitTesting
    -0.51
    ThroughAttribute
    -0.50
     lentejuelas
    -0.50
    ">//
    -0.50
    POSITIVE LOGITS
     ब्रेकडाउन
    0.30
    Parab
    0.29
     detail
    0.29
     Juga
    0.28
     uds
    0.28
    第
    0.28
    ebx
    0.28
    NumberOf
    0.27
     conos
    0.27
     топо
    0.27
    Activations Density 0.114%

    No Known Activations