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. 40-GEMMASCOPE-RES-16K
    6. 5787
    Prev
    Next
    INDEX
    Explanations

    references to military locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.41
     Jamaican
    -0.40
    Predict
    -0.40
    Alabama
    -0.40
     Alabama
    -0.38
    chiali
    -0.38
    conditioned
    -0.37
    uisine
    -0.37
    Conditional
    -0.36
     препратки
    -0.36
    POSITIVE LOGITS
     Dakota
    0.76
     Sioux
    0.75
     Fargo
    0.75
     Bismarck
    0.75
    Dakota
    0.68
     dakota
    0.67
     SD
    0.64
     Rapid
    0.64
     SDS
    0.63
     ND
    0.61
    Activations Density 0.212%

    No Known Activations