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. 15-GEMMASCOPE-RES-16K
    6. 5013
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms, particularly those related to scripts and functions commonly used in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.74
    addComponent
    -0.68
     AppCompat
    -0.66
    IFICATE
    -0.63
     réessayer
    -0.62
     REACTOR
    -0.62
     die
    -0.61
     bel
    -0.60
     le
    -0.59
     CALIFORNI
    -0.59
    POSITIVE LOGITS
     Shakspeare
    0.91
    ſelf
    0.90
    ſelves
    0.85
     avoient
    0.84
     Houſe
    0.80
     Monfieur
    0.79
     RIPRODUZIONE
    0.77
    Personendaten
    0.77
     Jefus
    0.76
     Chriftian
    0.76
    Activations Density 1.370%

    No Known Activations