© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2070
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between family members in a genealogical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <em>
    -0.41
    fael
    -0.39
    ."""
    -0.37
    型
    -0.37
    ↵↵
    -0.36
    符
    -0.36
    **
    -0.36
    ™
    -0.36
    TM
    -0.36
    sial
    -0.34
    POSITIVE LOGITS
    RenderAtEndOf
    1.09
    ChildScrollView
    0.94
    TintMode
    0.89
    Tikang
    0.87
    ItemBackground
    0.87
    tonode
    0.82
    ClassNotFound
    0.82
    Datuak
    0.81
     EClass
    0.78
    HideFlags
    0.77
    Activations Density 0.057%

    No Known Activations