© 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. 15906
    Prev
    Next
    INDEX
    Explanations

    names of places, people, or inventions related to specific locations or historical figures

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

    proper nouns and geographic locations.

    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
    er
    -0.97
    もしれません
    -0.60
    en
    -0.58
    ER
    -0.57
    ality
    -0.54
    り
    -0.50
    erle
    -0.48
    httphttps
    -0.48
    存于互联网档案馆
    -0.47
    erda
    -0.46
    POSITIVE LOGITS
    ing
    0.77
    ی
    0.73
    y
    0.66
    ING
    0.60
    ingar
    0.54
    й
    0.51
    ynomial
    0.49
     ​​
    0.48
    digarh
    0.47
    yng
    0.47
    Activations Density 2.130%

    No Known Activations