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. 10319
    Prev
    Next
    INDEX
    Explanations

    names of people and familial relationships

    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
    Rhestr
    -0.61
    WriteBarrier
    -0.55
    tagHelperRunner
    -0.53
    Otras
    -0.53
    
    -0.53
    Compartir
    -0.49
    хой
    -0.49
     Dall
    -0.48
    versaire
    -0.47
    ={`/
    -0.47
    POSITIVE LOGITS
     Rose
    0.63
     Domin
    0.63
     Salvatore
    0.62
     Domen
    0.60
    Rose
    0.59
     Anthony
    0.59
     Theresa
    0.57
    HostException
    0.56
     Vincent
    0.56
    MigrationBuilder
    0.56
    Activations Density 0.137%

    No Known Activations