© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7977
    Prev
    Next
    INDEX
    Explanations

    specific names and places related to news events, particularly in the context of legal proceedings and sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.59
     الرياضيه
    -0.58
    MLLoader
    -0.55
    ftagPool
    -0.55
    تقاوى
    -0.54
    requestCode
    -0.52
     propOrder
    -0.50
    xase
    -0.50
    stylers
    -0.50
    NameInMap
    -0.50
    POSITIVE LOGITS
     colombiano
    0.56
     Newcastle
    0.55
     colombiana
    0.52
     colomb
    0.51
    Newcastle
    0.50
     Colombian
    0.47
    reactstrap
    0.46
    toEqual
    0.44
     Colombia
    0.44
     Wilkes
    0.43
    Activations Density 0.615%

    No Known Activations