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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4523
    Prev
    Next
    INDEX
    Explanations

    keywords related to treatments, diseases, and medical conditions

    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
    Frequency
    -0.51
    Nå
    -0.51
    FREQUENCY
    -0.50
     Frequency
    -0.49
     Espagne
    -0.48
     age
    -0.47
    Արտաքին
    -0.46
    statistics
    -0.46
     AGE
    -0.45
    culada
    -0.45
    POSITIVE LOGITS
     onCreateView
    0.65
    ViewImports
    0.63
    GOTREF
    0.60
     "..\..\..\
    0.59
    الإنجليزية
    0.58
    DebuggerNonUser
    0.57
     invokingState
    0.56
    HasForeignKey
    0.56
    CloseOperation
    0.56
    RTLU
    0.56
    Activations Density 1.721%

    No Known Activations