© 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. 15663
    Prev
    Next
    INDEX
    Explanations

    terms related to international cooperation and counter-terrorism efforts

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

    mentions of Morocco and closely related proper nouns—covering its cities, officials, institutions, and the Western Sahara context.

    oai_token-act-pair · gpt-5Triggered 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
    -0.60
     CURIAM
    -0.50
    amazonaws
    -0.48
     Chriftian
    -0.48
     Singapur
    -0.46
     AssemblyCulture
    -0.45
    SuppressLint
    -0.45
    ::_('
    -0.44
     kaynağından
    -0.44
    KURZBESCHREIBUNG
    -0.43
    POSITIVE LOGITS
     käs
    0.38
    دانشنامهٔ
    0.38
     vastaan
    0.38
     Morocco
    0.37
    VYMaps
    0.36
     defaultstate
    0.36
     constituye
    0.36
     Infórmanos
    0.35
    úcar
    0.35
     Taktlose
    0.35
    Activations Density 0.066%

    No Known Activations