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
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8362
    Prev
    Next
    INDEX
    Explanations

    references to India and its various aspects or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neous
    -0.51
     Cornish
    -0.48
     requ
    -0.47
    UnusedPrivate
    -0.47
    quisite
    -0.47
     Calab
    -0.46
     ACCOM
    -0.46
    esian
    -0.44
    getic
    -0.44
    <0xAB>
    -0.43
    POSITIVE LOGITS
     India
    2.33
     Australia
    2.20
     Canada
    2.11
    India
    2.11
     France
    2.11
     Italy
    2.09
     Japan
    2.08
     Indonesia
    2.06
     Germany
    2.06
     China
    2.06
    Activations Density 0.937%

    No Known Activations