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-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23186
    Prev
    Next
    INDEX
    Explanations

    specific structured data or parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.79
    AxisAlignment
    -0.70
    BeginContext
    -0.69
    تقاوى
    -0.64
    Personendaten
    -0.62
    
    -0.59
     мәкал
    -0.58
    LayoutStyle
    -0.57
     Numerade
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
     respiración
    0.51
     plomo
    0.49
    queles
    0.48
     productividad
    0.47
     preghiera
    0.47
     discriminación
    0.46
     cooperación
    0.45
     inmediato
    0.45
     reputación
    0.45
     abundancia
    0.44
    Activations Density 0.808%

    No Known Activations