© 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. 20-GEMMASCOPE-RES-65K
    6. 626
    Prev
    Next
    INDEX
    Explanations

    conditional statements or clauses

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

    conditional statements and warnings

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

    conditional negative outcomes

    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
    bleau
    -0.63
     itſelf
    -0.63
    __':
    
    -0.62
    dubbo
    -0.59
    IPAC
    -0.55
    الحياه
    -0.55
    pero
    -0.54
     layui
    -0.53
     بتاريخ
    -0.53
    WebMethod
    -0.53
    POSITIVE LOGITS
     wrong
    0.81
     improperly
    0.76
     unchecked
    0.76
     improper
    0.74
     carelessly
    0.72
     incorrect
    0.72
    Wrong
    0.72
     careless
    0.72
     Wrong
    0.72
     too
    0.70
    Activations Density 0.088%

    No Known Activations