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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 2915
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or scientific measurements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -1.00
    expandindo
    -0.80
     disambiguazione
    -0.79
     EconPapers
    -0.76
    '}),
    -0.70
    PreferredItem
    -0.68
    NUMX
    -0.67
    يكب
    -0.67
    __':
    
    -0.67
    msgTypes
    -0.66
    POSITIVE LOGITS
     course
    0.45
    DIRECT
    0.45
    ;
    0.43
    LineColor
    0.43
     PLWABN
    0.42
    GetAll
    0.42
     umgeben
    0.42
    眷
    0.41
    course
    0.41
    toInt
    0.41
    Activations Density 0.448%

    No Known Activations