© 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. 10-GEMMASCOPE-RES-16K
    6. 11507
    Prev
    Next
    INDEX
    Explanations

    temporal words and phrases, particularly those indicating processes or sequences

    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
     poches
    -0.47
     wuß
    -0.47
     conozco
    -0.45
     feroit
    -0.45
     interesan
    -0.44
    chieht
    -0.44
     defStyle
    -0.43
     biß
    -0.43
     embarazadas
    -0.42
    ähteet
    -0.42
    POSITIVE LOGITS
     then
    0.87
     vervolgens
    0.71
     então
    0.70
     entonces
    0.68
     kemudian
    0.63
     thereupon
    0.62
    then
    0.60
     alors
    0.60
     thereby
    0.60
     następnie
    0.59
    Activations Density 0.287%

    No Known Activations