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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1789
    Prev
    Next
    INDEX
    Explanations

    themes related to parenting and the experiences of single mothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    StoryboardSegue
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    Према
    -0.45
    helfen
    -0.44
    حسب
    -0.44
    UAWEI
    -0.44
    mongoose
    -0.43
    ناك
    -0.43
     nahilalakip
    -0.43
    IFA
    -0.42
    POSITIVE LOGITS
     Theſe
    0.79
    Viitteet
    0.69
    HideFlags
    0.68
    CompilerServices
    0.68
     whoſe
    0.66
     Jefus
    0.65
     navigating
    0.65
     Anſ
    0.64
     Majefty
    0.61
     Beſ
    0.61
    Activations Density 0.128%

    No Known Activations