© 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. 3-GEMMASCOPE-RES-16K
    11. 2672
    Prev
    Next
    INDEX
    Explanations

    numerical values or symbols

    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
    Personendaten
    -0.95
    ValueStyle
    -0.83
     ujednoznacz
    -0.82
    }$​
    -0.81
    LayoutConstraint
    -0.79
    )");
    -0.76
    extAlignment
    -0.76
    ulemon
    -0.75
    SourceChecksum
    -0.72
    Datuak
    -0.72
    POSITIVE LOGITS
    getTable
    0.54
    口
    0.54
    ukone
    0.53
    역
    0.53
    jük
    0.52
    5
    0.51
    rab
    0.50
    0
    0.49
    hö
    0.48
     Duffy
    0.48
    Activations Density 0.203%

    No Known Activations