© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3298
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and connections between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     مرئيه
    -0.54
     nakalista
    -0.53
    RTHOOK
    -0.48
    expandindo
    -0.48
     utafitiHapana
    -0.46
    DockStyle
    -0.45
    RectangleBorder
    -0.45
    SourceChecksum
    -0.45
    úrese
    -0.45
     namentlich
    -0.44
    POSITIVE LOGITS
    addGroup
    0.76
     twin
    0.68
    Twin
    0.62
     Twin
    0.62
    twin
    0.59
     ब्रेकडाउन
    0.53
     crossorigin
    0.48
    Neither
    0.47
    ごめん
    0.46
     Neither
    0.46
    Activations Density 0.034%

    No Known Activations