Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 27658
    Prev
    Next
    INDEX
    Explanations

    concepts related to colonialism

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

    colonial history and biology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Irán
    -0.52
     Noruega
    -0.45
     Ministre
    -0.44
    menistan
    -0.43
    Math
    -0.42
     psychi
    -0.40
     Mathematics
    -0.40
     anest
    -0.40
     Ayuda
    -0.39
     Ucrania
    -0.39
    POSITIVE LOGITS
     Colonial
    2.27
     colonial
    2.20
    Colonial
    2.11
    colonial
    1.94
     colonialism
    1.47
     COLON
    1.35
     kolon
    1.14
     colon
    1.13
     Kolon
    1.09
     Colon
    1.09
    Activations Density 0.002%

    No Known Activations