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. 11474
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to starting a project or task

    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
     שוליים
    -0.49
    szön
    -0.46
    DateTimeField
    -0.45
     witnessed
    -0.44
    hålla
    -0.44
    ingtones
    -0.43
    putExtra
    -0.42
     unieke
    -0.42
     dikem
    -0.41
     onAnimation
    -0.41
    POSITIVE LOGITS
     Commencez
    0.78
     starters
    0.77
     start
    0.76
    pozdrawiam
    0.76
     Start
    0.74
     MainAxisSize
    0.73
     TAMBÉM
    0.72
     시작
    0.72
     Egli
    0.71
     begon
    0.70
    Activations Density 0.445%

    No Known Activations