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. 21-GEMMASCOPE-RES-16K
    6. 15216
    Prev
    Next
    INDEX
    Explanations

    markup language components and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.66
     traditionnels
    -0.65
     =>'
    -0.63
     ordinaires
    -0.63
     actuelles
    -0.63
     actuels
    -0.60
     appunto
    -0.58
     normaux
    -0.56
     spéciaux
    -0.56
    ).'
    -0.55
    POSITIVE LOGITS
     music
    0.65
     Music
    0.62
     file
    0.61
     MUSIC
    0.59
     color
    0.57
     Audio
    0.57
     Reverso
    0.57
     HTTP
    0.55
     audio
    0.55
    jacency
    0.54
    Activations Density 2.473%

    No Known Activations