© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 3830
    Prev
    Next
    INDEX
    Explanations

    expressions critiquing unnecessary elements or redundancy in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fear
    -0.25
    不容易
    -0.24
    uxxxx
    -0.24
    deauna
    -0.24
     terms
    -0.23
    ERVIS
    -0.23
     vertraut
    -0.23
    不敢
    -0.22
     Ex
    -0.22
     Severe
    -0.22
    POSITIVE LOGITS
     unnecessary
    1.29
     superfluous
    1.16
     inneces
    1.13
     useless
    1.05
     pointless
    1.04
     redundant
    1.03
     inutile
    1.02
     wasteful
    1.02
    useless
    0.99
    Useless
    0.98
    Activations Density 0.723%

    No Known Activations