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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10384
    Prev
    Next
    INDEX
    Explanations

    attributes and settings related to HTML and CSS structure

    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
    Vidite
    -0.49
    Risultati
    -0.46
    lück
    -0.44
    

    -0.44
    wartet
    -0.44
     informée
    -0.42
    Aholisi
    -0.40
    hyrchwyd
    -0.39
    fjspx
    -0.39
    ArgumentParser
    -0.39
    POSITIVE LOGITS
    =
    2.29
     =
    2.15
     $=
    1.93
     $=$
    1.81
    ='
    1.80
    ="
    1.78
    =$
    1.76
    =\
    1.76
    ={
    1.73
    =-
    1.68
    Activations Density 3.890%

    No Known Activations