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. 15-GEMMASCOPE-RES-16K
    6. 8690
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and understanding challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Demografie
    -0.59
    ›
    -0.51
     jsPsych
    -0.50
     Iy
    -0.47
    нительно
    -0.46
    UE
    -0.46
    felf
    -0.45
    TIPS
    -0.44
    Statistiche
    -0.43
     Sey
    -0.43
    POSITIVE LOGITS
     it
    1.56
     them
    1.35
     ervan
    0.97
     그것
    0.95
    +#+#
    0.91
     esso
    0.90
     dalamnya
    0.90
    它
    0.89
     оно
    0.86
     him
    0.86
    Activations Density 0.442%

    No Known Activations