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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4713
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to scientific collaboration and research activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.61
    ABULARY
    -0.56
     podjela
    -0.56
    XmlIgnore
    -0.52
    vrij
    -0.49
    ůvod
    -0.49
     alluminio
    -0.48
    WithIOException
    -0.47
     Hats
    -0.46
    agonia
    -0.45
    POSITIVE LOGITS
    +#+#
    0.77
     الرياضيه
    0.72
     protoimpl
    0.70
    GraphicsUnit
    0.68
    StructEnd
    0.68
     infine
    0.66
    fromnode
    0.66
     CiNii
    0.61
    Xna
    0.60
    bootstrapcdn
    0.59
    Activations Density 1.077%

    No Known Activations