Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10527
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and beliefs about social and political issues

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

    Preceding tokens of "would" or similar modal verbs

    np_acts-logits-general · gemini-2.0-flash

    conditional 'would'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بتاريخ
    -0.76
     autorytatywna
    -0.71
    ThroughAttribute
    -0.71
    ésultat
    -0.67
    WithIOException
    -0.66
    İstinadlar
    -0.66
    __':
    
    -0.65
    __":
    
    -0.64
     jLabel
    -0.64
    ]--;
    -0.63
    POSITIVE LOGITS
     would
    3.98
    would
    3.34
     Would
    3.07
    Would
    2.95
     WOULD
    2.77
     wouldn
    2.26
    wouldn
    1.96
     zou
    1.90
     sería
    1.89
     zouden
    1.88
    Activations Density 1.482%

    No Known Activations