© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 191
    Prev
    Next
    INDEX
    Explanations

    punctuation and structuring elements in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.48
     ComVisible
    -0.47
     whatever
    -0.47
    BeforeEach
    -0.44
    zarchiwizowane
    -0.44
     level
    -0.43
     you
    -0.43
     it
    -0.42
    izier
    -0.42
     something
    -0.42
    POSITIVE LOGITS
    PMailer
    0.77
    TagMode
    0.73
     Meksiku
    0.68
    
    0.66
     Efq
    0.62
    httphttps
    0.61
    ніципа
    0.60
    InjectAttribute
    0.60
    각주
    0.59
    はじめに
    0.59
    Activations Density 1.698%

    No Known Activations