© 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. 8960
    Prev
    Next
    INDEX
    Explanations

    references to authors and their contributions in a narrative context

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

    proper nouns, particularly people's names and surnames.

    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
     looks
    -0.36
    aksikan
    -0.35
     acuerdo
    -0.35
     acoged
    -0.34
     normalidad
    -0.34
     convertirse
    -0.33
     preju
    -0.33
     acceptance
    -0.33
     witnessed
    -0.33
     appreciation
    -0.33
    POSITIVE LOGITS
    fjspx
    0.74
     purposely
    0.66
    setVerticalGroup
    0.65
    httphttps
    0.65
     deliberately
    0.62
     chose
    0.60
     intentionally
    0.59
    chose
    0.59
     basing
    0.59
     sengaja
    0.57
    Activations Density 0.801%

    No Known Activations