© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    themes related to cultural values and their evolution over time

    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
    ніципалі
    -0.57
     disponibilités
    -0.56
     gynhyrchwyd
    -0.52
    RegressionTest
    -0.51
     Komunikasi
    -0.51
    IVEREF
    -0.50
     berätt
    -0.50
     scientifiques
    -0.47
     gebeten
    -0.47
     geholfen
    -0.46
    POSITIVE LOGITS
     advocating
    1.30
     advocate
    1.27
     advocates
    1.25
    advoc
    1.20
     advocated
    1.16
     emphasis
    1.15
     promotes
    1.10
     promote
    1.09
     promoting
    1.09
    倡
    1.04
    Activations Density 0.766%

    No Known Activations