© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 9079
    Prev
    Next
    INDEX
    Explanations

    expressions related to thoughtfulness or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.75
    SharedDtor
    -0.70
    ſelf
    -0.60
     NavController
    -0.59
    MigrationBuilder
    -0.56
     MongoClient
    -0.56
    anyahu
    -0.56
     myſelf
    -0.54
     vidare
    -0.54
    rungsseite
    -0.53
    POSITIVE LOGITS
    provoking
    0.57
     provoking
    0.56
     processes
    0.50
     process
    0.49
     leaders
    0.43
     proceso
    0.42
    Thought
    0.41
    out
    0.41
     Thought
    0.40
    thought
    0.40
    Activations Density 0.114%

    No Known Activations