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. 14-GEMMASCOPE-RES-16K
    6. 4329
    Prev
    Next
    INDEX
    Explanations

    terms related to e-commerce platforms and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.95
    OGND
    -0.88
     fince
    -0.72
    ՚
    -0.71
     chofe
    -0.68
     Chriftian
    -0.68
     Moslem
    -0.67
    "},
    
    -0.67
     itſelf
    -0.67
     myſelf
    -0.66
    POSITIVE LOGITS
     لينك
    0.50
    ScopeManager
    0.43
    mergeFrom
    0.41
     procedere
    0.40
    ErrUnexpectedEOF
    0.40
     الرياضيه
    0.39
    évaluateur
    0.38
     regular
    0.38
    起
    0.38
     I
    0.37
    Activations Density 1.234%

    No Known Activations