© 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. 33-GEMMASCOPE-RES-16K
    11. 1649
    Prev
    Next
    INDEX
    Explanations

    technical terms and indicators of complexity in code or legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.58
     OMITBAD
    -0.48
    Према
    -0.45
     Italijanski
    -0.44
    CrossRef
    -0.44
    stdc
    -0.43
    RTCK
    -0.42
    ToBounds
    -0.42
    webElementXpaths
    -0.40
    XmlAccessType
    -0.40
    POSITIVE LOGITS
     here
    4.28
     aquí
    3.17
    here
    3.08
     здесь
    3.00
     Here
    2.92
    Here
    2.88
     aqui
    2.78
     هنا
    2.72
     ici
    2.72
     aici
    2.69
    Activations Density 2.714%

    No Known Activations