© 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. 2-GEMMASCOPE-RES-16K
    11. 15087
    Prev
    Next
    INDEX
    Explanations

    references to the bottom or lowermost positions in a context, indicating the placement or importance of something at the lower end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     HasFactory
    -0.54
     trekken
    -0.47
    /*
    -0.45
     *
    -0.43
    vetrain
    -0.42
    ServletException
    -0.42
     INTERESAR
    -0.40
    quelize
    -0.40
    ]")]
    -0.40
    anskrit
    -0.40
    POSITIVE LOGITS
     bottom
    3.92
     Bottom
    3.69
    bottom
    3.67
    Bottom
    3.52
     BOTTOM
    3.28
    BOTTOM
    2.84
     bottoms
    2.80
    botto
    2.28
    底
    2.25
     botto
    2.11
    Activations Density 0.114%

    No Known Activations