© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39589
    Prev
    Next
    INDEX
    Explanations

    details about specific items, their attributes, and comparisons of their advantages and disadvantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     امريكا
    -0.67
    Chham
    -0.66
    ineno
    -0.65
    LookAnd
    -0.63
    ьаж
    -0.61
    RefNanny
    -0.60
    CodeDom
    -0.59
    resser
    -0.59
     >=",
    -0.59
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
    Each
    0.59
     Each
    0.59
     each
    0.56
     raisons
    0.55
    ずつ
    0.52
    各有
    0.52
    都有
    0.50
     contributing
    0.50
    씩
    0.49
     fiecare
    0.48
    Activations Density 0.081%

    No Known Activations