© 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. 40-GEMMASCOPE-RES-16K
    6. 1960
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to account-related terms and status updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schwierig
    -0.56
     difficult
    -0.55
     schweren
    -0.54
     speciale
    -0.53
     diverse
    -0.53
     gratuita
    -0.52
     kurze
    -0.51
     habituales
    -0.51
    difficult
    -0.51
     exitosa
    -0.51
    POSITIVE LOGITS
     Biôgrafia
    0.53
    windowFixed
    0.52
     jScrollPane
    0.49
     Docks
    0.45
    versammlung
    0.44
    delwed
    0.43
     anions
    0.42
    ristown
    0.42
     domains
    0.42
     нее
    0.42
    Activations Density 0.041%

    No Known Activations