© 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. 10-GEMMASCOPE-RES-16K
    11. 7066
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating dependency or variability in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Masyarakat
    -0.38
     Bersama
    -0.33
     Schä
    -0.33
     saati
    -0.32
    lastTime
    -0.32
     Ganzen
    -0.31
     đào
    -0.31
    了一声
    -0.31
     Schre
    -0.31
     proprement
    -0.31
    POSITIVE LOGITS
     depending
    1.41
    depending
    1.40
     Depending
    1.25
     dependiendo
    1.24
    Depending
    1.24
     Depends
    1.23
    Depends
    1.20
    depends
    1.20
     depends
    1.19
     afhankelijk
    1.18
    Activations Density 0.326%

    No Known Activations