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-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11263
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    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
     Photocase
    -0.74
    IsContent
    -0.70
     Chrift
    -0.67
    Datuak
    -0.66
     MainAxisSize
    -0.66
    Хьажоргаш
    -0.64
    exitRule
    -0.64
    ImageContext
    -0.63
     فريبيس
    -0.62
     Reſ
    -0.62
    POSITIVE LOGITS
     whilst
    0.46
     skall
    0.42
    Whilst
    0.42
     Whilst
    0.40
    miştir
    0.39
     данного
    0.38
     již
    0.38
     utilizar
    0.38
     welcher
    0.36
     jeżeli
    0.36
    Activations Density 0.176%

    No Known Activations