© 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. 2182
    Prev
    Next
    INDEX
    Explanations

    names and titles of characters involved in dialogue and interactions

    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
     Monfieur
    -0.61
     Anſ
    -0.60
     Diſ
    -0.59
     Efq
    -0.58
     ſte
    -0.58
     faſt
    -0.58
     ſind
    -0.56
     pleaſure
    -0.55
     Eſ
    -0.54
     itſelf
    -0.54
    POSITIVE LOGITS
     Roman
    1.32
    Roman
    1.14
     ROMAN
    1.09
     рим
    1.05
     Rome
    1.05
     romanos
    1.05
     römischen
    1.04
     Romans
    1.03
     romana
    1.02
     romano
    0.99
    Activations Density 0.219%

    No Known Activations