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. 11821
    Prev
    Next
    INDEX
    Explanations

    action verbs and gerunds related to scientific processes and data analysis

    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
    setopt
    -0.85
     Folge
    -0.75
     getRule
    -0.74
    ্ন
    -0.71
    acre
    -0.71
     Ruh
    -0.71
     flesta
    -0.69
    angeran
    -0.69
     Hornets
    -0.68
    égard
    -0.68
    POSITIVE LOGITS
    ting
    1.40
    ating
    1.32
    ging
    1.29
    ning
    1.21
    NING
    1.20
    izing
    1.19
    ming
    1.16
    TING
    1.16
    oring
    1.15
    cting
    1.14
    Activations Density 1.586%

    No Known Activations