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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8689
    Prev
    Next
    INDEX
    Explanations

    action verbs related to creation and building processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEGGI
    -0.70
    providedIn
    -0.69
    @[+][
    -0.68
     ProtoMessage
    -0.66
    inSlope
    -0.66
    principalColumn
    -0.66
    ContentAlignment
    -0.66
    RemoteException
    -0.64
    IsContent
    -0.64
     للمعارف
    -0.64
    POSITIVE LOGITS
     make
    2.01
    make
    1.99
     made
    1.90
    Make
    1.89
     Make
    1.87
     MAKE
    1.82
    makes
    1.82
    made
    1.81
     making
    1.79
    Making
    1.78
    Activations Density 0.140%

    No Known Activations