© 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. 6041
    Prev
    Next
    INDEX
    Explanations

    emphatic negations or affirmations

    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
    MAT
    -0.45
    LIN
    -0.45
    ENC
    -0.44
    IGR
    -0.44
    MET
    -0.44
    SEG
    -0.44
    CUL
    -0.43
    VIS
    -0.43
    SERV
    -0.42
    VEL
    -0.42
    POSITIVE LOGITS
     BOTH
    1.51
     REALLY
    1.48
     ANYTHING
    1.46
     EVERY
    1.45
     ONLY
    1.44
     ANY
    1.44
     VERY
    1.44
     HUGE
    1.43
     ALWAYS
    1.42
     ALL
    1.41
    Activations Density 0.449%

    No Known Activations