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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 6360
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical structures and their properties, especially in relation to ideals and dimensions in algebraic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hancock
    -0.65
    illot
    -0.63
    illo
    -0.61
    psycho
    -0.61
    ILLO
    -0.61
     Cass
    -0.60
     Worthington
    -0.60
     Stanton
    -0.60
     JC
    -0.60
     Hoff
    -0.60
    POSITIVE LOGITS
     Chapin
    0.82
    IUrlHelper
    0.69
    AxisAlignment
    0.66
     ITIS
    0.64
     Mullins
    0.63
     Katja
    0.63
     Matsumoto
    0.62
     Martha
    0.61
     IEEE
    0.61
     Colbert
    0.60
    Activations Density 1.077%

    No Known Activations