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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6690
    Prev
    Next
    INDEX
    Explanations

    information related to computer hardware specifications and memory details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.59
     NSCoder
    -0.56
     ActionListener
    -0.55
    AddTagHelper
    -0.54
    
    -0.53
    úgó
    -0.52
    tagHelperRunner
    -0.50
     $_"
    -0.48
    paroles
    -0.48
    arResult
    -0.47
    POSITIVE LOGITS
     RAM
    0.62
     ram
    0.61
    Memory
    0.46
    Ram
    0.45
    RAM
    0.45
     Ram
    0.45
     ब्रेकडाउन
    0.44
     memory
    0.43
     MEMORY
    0.41
     Memory
    0.39
    Activations Density 0.424%

    No Known Activations