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. 24-GEMMASCOPE-RES-131K
    6. 1058
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and calculations related to data analysis

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

    calculating and mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.54
    
    -0.53
     betweenstory
    -0.48
     "..\..\
    -0.48
    ьаж
    -0.44
    +#+
    -0.40
    pantalones
    -0.40
     insuffisamment
    -0.40
    WriteBarrier
    -0.39
    ffect
    -0.38
    POSITIVE LOGITS
     subtract
    0.65
    Portale
    0.62
     calculate
    0.60
     subtracting
    0.58
    算
    0.57
     multiply
    0.56
     disambiguazione
    0.54
     calculating
    0.54
     محاس
    0.54
     subtracted
    0.53
    Activations Density 0.135%

    No Known Activations