© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 8350
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and terms related to institutions, scientific fields, and research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.52
     intptr
    -0.47
    TagHelper
    -0.40
     CanadaChoose
    -0.40
    NameInMap
    -0.37
     cherchés
    -0.37
    原始内容存档于
    -0.37
     Arena
    -0.36
    agent
    -0.36
    Arena
    -0.36
    POSITIVE LOGITS
     Ac
    2.03
     ac
    2.02
     acc
    1.98
     Acc
    1.91
    Ac
    1.81
     ACC
    1.78
    Acc
    1.77
    acc
    1.72
    ac
    1.68
     AC
    1.66
    Activations Density 1.751%

    No Known Activations