© 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. 34-GEMMASCOPE-RES-16K
    11. 64
    Prev
    Next
    INDEX
    Explanations

    phrases related to data management and processing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wenigen
    -0.41
    łaszcza
    -0.39
     wenige
    -0.39
    AlterField
    -0.38
    BibitemShut
    -0.35
     vieles
    -0.35
    WithMany
    -0.35
    Many
    -0.34
     sekaligus
    -0.34
    だけでなく
    -0.33
    POSITIVE LOGITS
     some
    2.44
     somehow
    2.42
     algum
    2.36
     algún
    2.28
     alguma
    2.27
     alguna
    2.20
    some
    2.16
     nějak
    2.05
     irgende
    1.98
     somewhere
    1.95
    Activations Density 1.571%

    No Known Activations