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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39438
    Prev
    Next
    INDEX
    Explanations

    terms related to medical phenomena and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -1.09
    extAlignment
    -0.96
    httphttps
    -0.96
    цездатний
    -0.93
    ImageContext
    -0.91
    IsContent
    -0.90
    queryInterface
    -0.90
    Diweddarwch
    -0.89
     فريبيس
    -0.89
     beginnetje
    -0.88
    POSITIVE LOGITS
    </i>
    0.41
     of
    0.40
    во
    0.39
    マイ
    0.39
    FL
    0.38
     has
    0.38
    Job
    0.38
     for
    0.37
     case
    0.36
    ,
    0.36
    Activations Density 0.205%

    No Known Activations