© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10034
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with promotions and high-ranking positions within organizations or bureaucracies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chia
    -0.47
    ak
    -0.44
     R
    -0.44
    module
    -0.43
    援
    -0.43
    ту
    -0.42
    lax
    -0.41
     fog
    -0.41
    aks
    -0.41
     let
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.86
    Datuak
    0.81
    ArgsConstructor
    0.80
     Efq
    0.77
     venons
    0.74
     négociations
    0.74
     doubtnut
    0.74
    RTLD
    0.73
     feroit
    0.72
    StructEnd
    0.70
    Activations Density 0.281%

    No Known Activations