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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56858
    Prev
    Next
    INDEX
    Explanations

    references to academic departments and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     something
    -0.45
    Manbalar
    -0.44
     if
    -0.43
     though
    -0.43
     when
    -0.43
     do
    -0.42
     no
    -0.41
     cho
    -0.41
    kosh
    -0.41
    ostoma
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.78
    tagHelperRunner
    0.73
    MemoryWarning
    0.71
    />";
    0.68
     emeritus
    0.66
    NUMX
    0.65
    Trama
    0.64
     **/
    
    0.63
    Hentet
    0.63
     bezoek
    0.62
    Activations Density 0.010%

    No Known Activations