© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2382
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their affiliations

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

    specific restaurant, food, or location names in Malaysia.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    references specific to Malaysia—its places, currency, cuisine, and political figures/institutions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    Malaysian names, places, and culturally specific terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.55
     виправивши
    -0.43
    úgó
    -0.42
     Exactos
    -0.39
    allowNull
    -0.37
     MainAxisSize
    -0.36
    Hawks
    -0.34
     heiß
    -0.33
    NewGuid
    -0.33
    事儿
    -0.33
    POSITIVE LOGITS
     Malaysian
    0.81
     Malaysia
    0.80
    Malaysia
    0.73
     Malay
    0.66
    AYSIA
    0.65
     Lumpur
    0.64
    Malay
    0.63
    UALA
    0.63
     Kuala
    0.58
     malaysia
    0.57
    Activations Density 0.277%

    No Known Activations