© 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. 27-GEMMASCOPE-RES-16K
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    mentions of leadership changes or appointments in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.48
    decine
    -0.47
    cluse
    -0.44
     Ovid
    -0.43
     Aufwand
    -0.43
     itſelf
    -0.42
     bezeichneter
    -0.42
     spoilt
    -0.42
    Marshall
    -0.41
    новништво
    -0.41
    POSITIVE LOGITS
     appointed
    0.89
     appointing
    0.82
     appointment
    0.81
     leadership
    0.77
     appoint
    0.77
     Appointed
    0.75
     APPOINT
    0.73
     Appointment
    0.71
    就任
    0.71
    appointed
    0.69
    Activations Density 0.505%

    No Known Activations