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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15635
    Prev
    Next
    INDEX
    Explanations

    references to laws and legal terminology within discussions about political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.94
    SourceChecksum
    -0.76
     AppColors
    -0.75
     vVar
    -0.74
    ><><
    -0.70
     photolibrary
    -0.69
     Профиль
    -0.67
    setVerticalGroup
    -0.65
    RRect
    -0.65
    OOTDTY
    -0.64
    POSITIVE LOGITS
    LookAnd
    0.71
     nahilalakip
    0.59
    ↵
    0.58
    its
    0.56
    httphttps
    0.55
    ...
    0.52
    can
    0.48
     onCreateView
    0.48
    contentLoaded
    0.47
     باخ
    0.47
    Activations Density 1.834%

    No Known Activations