© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10255
    Prev
    Next
    INDEX
    Explanations

    verbs related to showing or demonstrating information or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     topik
    -0.37
     parfums
    -0.36
     Gewebe
    -0.36
     Erinnerungen
    -0.36
     Zufall
    -0.35
     Zeitpunkt
    -0.33
     saveur
    -0.33
     krijg
    -0.33
     voces
    -0.33
     informacija
    -0.32
    POSITIVE LOGITS
     Showing
    1.21
     showing
    1.18
    Showing
    1.09
    showing
    1.06
     shown
    1.05
     Shown
    1.05
     SHOWING
    1.02
     showed
    1.02
     Shows
    1.02
     demonstrating
    0.99
    Activations Density 0.185%

    No Known Activations