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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 58467
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.60
    GEBURTSDATUM
    -0.47
    setWeight
    -0.46
     beträgt
    -0.43
     příjem
    -0.42
     kroppen
    -0.42
    ktas
    -0.41
     cười
    -0.40
    流石
    -0.40
     rígido
    -0.40
    POSITIVE LOGITS
    AddRange
    1.58
    ModelSerializer
    1.24
    minecraftforge
    1.02
     disambiguazione
    1.01
    verwijspagina
    0.98
     $__
    0.95
    mbggenerated
    0.94
     ProtoMessage
    0.91
     incomplète
    0.90
    Vidite
    0.88
    Activations Density 0.000%

    No Known Activations