© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    references to data types and their attributes in a structured format

    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
     élevées
    -0.63
    expandindo
    -0.60
     Nacionales
    -0.58
     mijne
    -0.53
     estimés
    -0.53
     Schwert
    -0.53
     suivants
    -0.53
     défaite
    -0.51
     industriels
    -0.51
     privée
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.79
    bitField
    0.75
    httphttps
    0.71
     незавершена
    0.69
    GraphicsUnit
    0.67
    rimônio
    0.63
    fillType
    0.61
    dafx
    0.61
     hObject
    0.60
     doInBackground
    0.60
    Activations Density 0.418%

    No Known Activations