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. 4089
    Prev
    Next
    INDEX
    Explanations

    key-value pair assignments and their relationships in structured data

    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
    Viitteet
    -0.59
    Descripció
    -0.58
     recensement
    -0.58
    انگلیسی
    -0.56
    <h1>
    -0.56
    tă
    -0.55
    Посилання
    -0.54
    ódó
    -0.52
     voud
    -0.50
     كمان
    -0.50
    POSITIVE LOGITS
    ::::::::
    0.71
     Signalez
    0.68
     IBOutlet
    0.67
     Berikut
    0.67
     CGRectMake
    0.65
    CloseOperation
    0.62
    orteur
    0.62
     snippetHide
    0.61
     MainAxisSize
    0.61
    toolkit
    0.60
    Activations Density 0.534%

    No Known Activations