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. 12-GEMMASCOPE-RES-16K
    6. 4719
    Prev
    Next
    INDEX
    Explanations

    quotes from various individuals in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jScrollPane
    -0.64
    ChildScrollView
    -0.63
     ComVisible
    -0.59
    ScopeManager
    -0.58
     ModelExpression
    -0.56
    
    -0.53
    setVerticalGroup
    -0.51
     resourceCulture
    -0.51
     CreateTagHelper
    -0.50
    GEBURTSDATUM
    -0.50
    POSITIVE LOGITS
     saken
    0.59
    ">//
    0.54
     }}$.
    0.53
    脚注の使い方
    0.53
    ¹.
    0.53
    '.
    0.52
    \,.
    0.52
    $.\\
    0.52
    ecake
    0.51
    **.
    0.51
    Activations Density 0.145%

    No Known Activations