Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53147
    Prev
    Next
    INDEX
    Explanations

    references to the concept of inclusion or entities involved in an action or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preposition after number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.87
     myſelf
    -0.79
     ſche
    -0.75
    évaluateur
    -0.73
     Efq
    -0.71
     purpoſe
    -0.69
     ―――――
    -0.68
     Monfieur
    -0.68
     occaf
    -0.66
     eſ
    -0.66
    POSITIVE LOGITS
    исленность
    0.65
    fromnode
    0.60
    yled
    0.59
    UniformLocation
    0.50
    executeQuery
    0.49
    endregion
    0.49
     sudad
    0.49
    databind
    0.48
    bellar
    0.48
     StyleSheet
    0.47
    Activations Density 0.002%

    No Known Activations