© 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. 18-GEMMASCOPE-RES-16K
    11. 921
    Prev
    Next
    INDEX
    Explanations

    references to funding and research institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    German institutions or patents

    np_acts-logits-general · gemini-2.0-flash

    German entities and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.21
     houſe
    -1.21
     purpoſe
    -1.16
     ſeveral
    -1.14
     myſelf
    -1.13
     ſtate
    -1.12
     Jefus
    -1.11
     Diſ
    -1.09
     pleaſure
    -1.08
     themſelves
    -1.08
    POSITIVE LOGITS
     German
    0.73
     استنادى
    0.67
     Germany
    0.67
     GmbH
    0.63
    thansa
    0.62
    German
    0.62
     alemão
    0.61
     Germans
    0.60
    Germany
    0.58
     Duitse
    0.56
    Activations Density 0.670%

    No Known Activations