© 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. 31-GEMMASCOPE-RES-16K
    11. 3575
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reflections on personal beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    periods and sentence endings that conclude personal reflections or emotional statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dobra
    -0.49
     resourceCulture
    -0.49
    適合
    -0.48
     auffi
    -0.48
     households
    -0.48
    eader
    -0.48
    こちらは
    -0.47
     patente
    -0.47
     hare
    -0.47
     stork
    -0.46
    POSITIVE LOGITS
     watching
    0.64
    Watching
    0.60
     seeing
    0.58
     hearing
    0.57
     Watching
    0.54
    SequentialGroup
    0.52
    watching
    0.51
     ever
    0.50
    Whenever
    0.50
    Seeing
    0.50
    Activations Density 0.446%

    No Known Activations