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. 25-GEMMASCOPE-RES-16K
    6. 3471
    Prev
    Next
    INDEX
    Explanations

    content related to mobile applications and their development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -0.84
    berdayakan
    -0.81
     loosing
    -0.74
     realy
    -0.74
     daß
    -0.73
     = 
    -0.73
     muß
    -0.70
     definately
    -0.70
     insure
    -0.66
     eachother
    -0.65
    POSITIVE LOGITS
    Suppose
    1.02
     Afterward
    0.89
     Suppose
    0.86
     ;
    0.75
    . 
    0.73
     afterward
    0.69
    ⮚
    0.69
    Hence
    0.69
     
    0.67
     '}
    0.66
    Activations Density 0.120%

    No Known Activations