© 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. 544
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and operations involving variables

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

    mathematical expressions and variables in a structured format

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

    variable assignments using 'Let'

    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
    </strong>
    -0.79
    ↵
    -0.73
    </em>
    -0.68
    ↵↵
    -0.63
     [
    -0.62
    !”
    -0.61
     $>
    -0.60
    !</
    -0.60
    <em>
    -0.59
    </h2>
    -0.58
    POSITIVE LOGITS
    Datuak
    0.86
     EconPapers
    0.79
     bezeichneter
    0.76
    expandindo
    0.74
    +#+#
    0.74
     tartalomajánló
    0.72
     noDo
    0.71
    ölkerung
    0.70
     الاطلاع
    0.70
     Monfieur
    0.70
    Activations Density 0.009%

    No Known Activations