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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4565
    Prev
    Next
    INDEX
    Explanations

    ideas and phrases related to choosing or following a path in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deleteAll
    -0.45
    nachweis
    -0.43
    incoming
    -0.43
     transmissão
    -0.43
    龄
    -0.42
    ül
    -0.42
    ercito
    -0.42
     pitié
    -0.42
     forfait
    -0.42
     жало
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    1.40
    findpost
    1.24
    SharedCtor
    1.01
    setVerticalGroup
    0.97
    abestanden
    0.97
    ValueStyle
    0.96
     disambiguazione
    0.95
    protoimpl
    0.94
     path
    0.93
    SourceChecksum
    0.93
    Activations Density 0.417%

    No Known Activations