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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 12835
    Prev
    Next
    INDEX
    Explanations

    specific mathematical expressions and symbols related to sequences and series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.60
    IsContent
    -0.59
    MessageOf
    -0.57
    AccessorTable
    -0.55
     فريبيس
    -0.53
    AnchorStyles
    -0.52
    цездатний
    -0.52
    UnsafeEnabled
    -0.52
     didReceive
    -0.49
     AssemblyVersion
    -0.48
    POSITIVE LOGITS
     Meksika
    0.43
    Spécification
    0.39
     Turquía
    0.38
    sarung
    0.38
     cible
    0.37
    ToUse
    0.36
     lápiz
    0.36
     špec
    0.35
    LEGGI
    0.35
    Target
    0.35
    Activations Density 1.325%

    No Known Activations