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. 4-GEMMASCOPE-RES-16K
    6. 774
    Prev
    Next
    INDEX
    Explanations

    terms related to collectiveness and community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsxFileName
    -0.75
    expandindo
    -0.71
    Cour
    -0.65
    שע
    -0.64
     oop
    -0.64
     phonics
    -0.61
     Darn
    -0.60
     Cour
    -0.60
     Scud
    -0.60
     Ston
    -0.59
    POSITIVE LOGITS
     collective
    2.01
    collective
    1.86
    Collective
    1.83
     Collective
    1.83
     collectively
    1.51
     kollek
    1.39
     colectiva
    1.18
     collectif
    1.15
    集体
    1.12
     colectivo
    1.04
    Activations Density 0.138%

    No Known Activations