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. 19-GEMMASCOPE-RES-16K
    6. 15665
    Prev
    Next
    INDEX
    Explanations

    tokens indicating the presence of binary or boolean conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <strong>
    -0.66
    GEBURTSDATUM
    -0.65
     مرئيه
    -0.64
     excru
    -0.64
    jsii
    -0.63
     CreateTagHelper
    -0.62
    ίας
    -0.62
    /**
    -0.62
      
    -0.61
     distanciation
    -0.59
    POSITIVE LOGITS
    EnableWeb
    0.70
    RefNanny
    0.57
    mặt
    0.55
    олові
    0.52
    Zobacz
    0.51
    íslu
    0.50
    ტერ
    0.50
    bootstrapcdn
    0.49
    inheritDoc
    0.49
    ikita
    0.49
    Activations Density 0.125%

    No Known Activations