© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1349
    Prev
    Next
    INDEX
    Explanations

    references to ramps and related infrastructure terms

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

    the word "ramp" and its variations in terms of context related to increasing production or efforts

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

    ramp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.89
     esternos
    -0.86
    urlpatterns
    -0.82
     referenties
    -0.76
    RegistryLite
    -0.75
    BeginContext
    -0.74
    writeFieldEnd
    -0.71
    Geplaatst
    -0.71
     disambiguazione
    -0.70
    PRWEB
    -0.69
    POSITIVE LOGITS
     Ramp
    1.00
     ramp
    0.98
     ramps
    0.96
    Ramp
    0.92
    ramp
    0.78
     raiſ
    0.68
    antly
    0.67
     Efq
    0.60
     faſt
    0.59
     Jefus
    0.59
    Activations Density 0.016%

    No Known Activations