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. 12119
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate suitability and compatibility of products or concepts

    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
     falando
    -0.52
    iestety
    -0.50
     שוליים
    -0.50
     سكانية
    -0.49
    meneu
    -0.49
     heridos
    -0.48
     Hacking
    -0.48
    OTTEN
    -0.48
    determined
    -0.48
    ClientSize
    -0.47
    POSITIVE LOGITS
    XmlType
    0.64
    findpost
    0.63
     suitable
    0.56
    adaptiveStyles
    0.56
     ProtoMessage
    0.53
    jsii
    0.51
     eignet
    0.51
     sowohl
    0.51
    Modules
    0.50
     itſelf
    0.50
    Activations Density 0.206%

    No Known Activations