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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6898
    Prev
    Next
    INDEX
    Explanations

    negative phrases or words indicating caution and resistance

    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
     EconPapers
    -0.66
    StoryboardSegue
    -0.65
    Rhestr
    -0.59
    parsedMessage
    -0.58
    MessageTagHelper
    -0.56
     gynhyrchwyd
    -0.54
     ब्रेकडाउन
    -0.51
    本当は
    -0.51
    ConstraintMaker
    -0.50
    Хьажоргаш
    -0.50
    POSITIVE LOGITS
     wasting
    0.67
     waste
    0.65
     dwelling
    0.64
     rush
    0.61
     dwell
    0.59
     rushing
    0.58
     worrying
    0.57
     obs
    0.56
     fret
    0.55
     wasted
    0.54
    Activations Density 0.532%

    No Known Activations