© 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. 17-GEMMASCOPE-RES-16K
    6. 5382
    Prev
    Next
    INDEX
    Explanations

    references to flight models and aircraft specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offerts
    -0.61
     Wiktionnaire
    -0.60
    expandindo
    -0.60
    ://"
    -0.58
    сылкі
    -0.57
     surla
    -0.53
    yectos
    -0.51
     énergé
    -0.51
    Revenir
    -0.51
     ostavi
    -0.50
    POSITIVE LOGITS
     realistic
    1.64
     realism
    1.57
     Realistic
    1.49
    Realistic
    1.34
    realistic
    1.32
     realistically
    1.25
     réaliste
    1.21
     realista
    1.18
     simulated
    1.15
     Realism
    1.13
    Activations Density 0.507%

    No Known Activations