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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2641
    Prev
    Next
    INDEX
    Explanations

    specific patterns or structures in data formatting related to a system's technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ๆ
    -0.56
     my
    -0.55
     me
    -0.52
    PyErr
    -0.52
     Hen
    -0.49
     H
    -0.46
    шту
    -0.46
     fibras
    -0.46
     kell
    -0.45
    – 
    -0.45
    POSITIVE LOGITS
     Majefty
    1.25
     pleaſure
    1.17
     purpoſe
    1.16
     Reſ
    1.08
     ་་
    1.08
     uſ
    1.08
     Monfieur
    1.07
     ſche
    1.06
     ―――――
    1.05
    verwijspagina
    1.04
    Activations Density 0.878%

    No Known Activations