© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2268
    Prev
    Next
    INDEX
    Explanations

    references to investigations and political situations, particularly involving candidates and ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.41
    afficheront
    -0.39
     mData
    -0.36
     Wiktionnaire
    -0.33
     Salter
    -0.33
    MessageState
    -0.31
    न्दर्भ
    -0.31
    lhes
    -0.31
     fellow
    -0.31
    hesda
    -0.31
    POSITIVE LOGITS
     again
    1.60
    again
    1.42
    Again
    1.39
     Again
    1.34
     AGAIN
    1.30
     nuevamente
    1.27
     novamente
    1.24
     nuovamente
    1.17
     снова
    1.12
     igjen
    1.10
    Activations Density 0.734%

    No Known Activations