© 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. 35-GEMMASCOPE-RES-16K
    11. 11716
    Prev
    Next
    INDEX
    Explanations

    references to errors, deficiencies, and the need for corrective actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.59
    argout
    -0.50
     disambiguazione
    -0.47
    HasAnnotation
    -0.46
    tawesome
    -0.45
    Personendaten
    -0.45
     pinulongan
    -0.44
    +#+
    -0.41
    CharSequence
    -0.41
     &___
    -0.40
    POSITIVE LOGITS
     flaws
    2.23
     weaknesses
    1.98
     defects
    1.98
     deficiencies
    1.88
     faults
    1.82
     shortcomings
    1.78
     flaw
    1.73
     imperfections
    1.72
     Defects
    1.55
     weakness
    1.47
    Activations Density 0.962%

    No Known Activations