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. 2830
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or formatted information

    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
     ||=
    -0.51
    гей
    -0.50
    OfMonth
    -0.48
     sud
    -0.46
     traite
    -0.45
     meeting
    -0.44
    Ṛ
    -0.43
     sooner
    -0.42
    agie
    -0.41
     Nagy
    -0.41
    POSITIVE LOGITS
    ########.
    1.00
    expandindo
    0.96
    Vidite
    0.92
    ⓧ
    0.82
    
    0.82
    НИК
    0.82
    IContainer
    0.79
    Datuak
    0.79
     дописавши
    0.78
    afficheront
    0.77
    Activations Density 1.715%

    No Known Activations