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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 10893
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data structures and processing in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoday
    -0.48
     lạ
    -0.46
     attribué
    -0.45
    gan
    -0.43
     anlay
    -0.42
    caine
    -0.42
     obstante
    -0.41
    го
    -0.41
     schuld
    -0.41
     sharp
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.78
     <>",
    0.72
    ImageContext
    0.72
     snippetHide
    0.71
     ModelExpression
    0.71
     &___
    0.69
    ChildScrollView
    0.69
    mergeFrom
    0.69
     ivelany
    0.67
     AppCompatTheme
    0.66
    Activations Density 0.606%

    No Known Activations