© 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. 6765
    Prev
    Next
    INDEX
    Explanations

    phrases related to purification and transformation processes

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

    Extending, renaming, or controlling something

    np_acts-logits-general · gemini-2.0-flash

    extend, learning, controlling, rename, keeping, waterproof, join

    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
     Efq
    -0.76
     ſche
    -0.72
     itſelf
    -0.71
     greateſt
    -0.70
     pleaſure
    -0.68
     houſe
    -0.68
     purpoſe
    -0.68
     iſt
    -0.64
     Jefus
    -0.63
     Diſ
    -0.63
    POSITIVE LOGITS
    oa̍t
    0.82
     re
    0.63
     bring
    0.62
     dem
    0.58
    WebElementEntity
    0.57
    將
    0.56
    EndProject
    0.56
     Infórmanos
    0.55
     put
    0.55
    把
    0.55
    Activations Density 0.864%

    No Known Activations