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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2030
    Prev
    Next
    INDEX
    Explanations

    phrases relating to specificity and conditions

    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
    multirow
    -0.37
    YTA
    -0.36
     inadvertently
    -0.34
    intervento
    -0.33
    effetto
    -0.33
    исленность
    -0.32
     Epile
    -0.32
    щин
    -0.32
     offender
    -0.32
     boiled
    -0.32
    POSITIVE LOGITS
     certain
    0.90
    certain
    0.90
     Certain
    0.90
    Certain
    0.89
     tertentu
    0.84
    特定
    0.77
     bestimmten
    0.75
     CERTAIN
    0.75
     bepaalde
    0.75
     determinada
    0.74
    Activations Density 0.541%

    No Known Activations