© 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. 585
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and phrases, especially in legal and programming contexts

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

    references to programming code and associated documentation

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

    planning permission or plans

    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
    TagMode
    -0.59
     оригіналу
    -0.50
    SequentialGroup
    -0.48
     ennen
    -0.48
     fallu
    -0.46
    before
    -0.42
     cristianismo
    -0.41
    mittel
    -0.41
     före
    -0.41
    AndEndTag
    -0.40
    POSITIVE LOGITS
    
    0.84
    expandindo
    0.79
    esModule
    0.74
    Personendaten
    0.69
     getRule
    0.66
     متعلقه
    0.66
    Funciones
    0.60
     nahilalakip
    0.60
     ]];
    0.60
    APES
    0.59
    Activations Density 0.126%

    No Known Activations