© 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. 9-GEMMASCOPE-RES-16K
    11. 6974
    Prev
    Next
    INDEX
    Explanations

    segments related to boolean values, particularly those indicating 'true' or 'false'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.61
     kasarigan
    -0.60
    tabular
    -0.60
    bootstrapcdn
    -0.60
     dAtA
    -0.60
    fjspx
    -0.60
    nyk
    -0.57
     nip
    -0.56
    ollectionView
    -0.56
     Tivoli
    -0.56
    POSITIVE LOGITS
     false
    2.20
    false
    2.02
     False
    1.98
    False
    1.89
     FALSE
    1.58
    FALSE
    1.43
     falso
    1.34
     falsos
    1.27
     falsa
    1.27
     falsely
    1.16
    Activations Density 0.064%

    No Known Activations