© 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. 35-GEMMASCOPE-RES-16K
    11. 6647
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to emphasis or assertion

    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
     *++
    -0.45
    eleste
    -0.39
     casualties
    -0.39
    ospels
    -0.38
    similar
    -0.38
    InitVars
    -0.38
    ikyuu
    -0.38
     propOrder
    -0.37
    Clik
    -0.37
    Hrs
    -0.37
    POSITIVE LOGITS
    zelfde
    0.77
     same
    0.71
     pesky
    0.70
    チール
    0.63
     particular
    0.61
     fateful
    0.56
     fameux
    0.56
     moment
    0.54
     stessa
    0.54
     SAME
    0.54
    Activations Density 0.271%

    No Known Activations