© 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. 9281
    Prev
    Next
    INDEX
    Explanations

    key events and announcements related to individuals' actions and decisions

    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
     critics
    -0.40
     Critics
    -0.39
     critic
    -0.37
    emples
    -0.36
     Critic
    -0.35
    ByExample
    -0.35
    Critic
    -0.34
     compara
    -0.33
    Critics
    -0.33
     crítica
    -0.33
    POSITIVE LOGITS
     announcement
    1.27
     announced
    1.07
     announcements
    1.05
     announce
    1.04
     Announcement
    1.00
     anúncio
    0.97
     ANNOUNC
    0.96
     announcing
    0.96
    宣布
    0.94
    Announcement
    0.93
    Activations Density 0.464%

    No Known Activations