© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14328
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and personal experiences

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

    Sentences starting with "I [auxiliary verb]"

    np_acts-logits-general · gemini-2.0-flash

    I think/remember/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.70
     المعيارى
    -0.69
    
    -0.65
    లాలు
    -0.63
    Tikang
    -0.62
    
    -0.61
    JspWriter
    -0.58
    ErrUnexpectedEOF
    -0.57
    دانشنامهٔ
    -0.55
    TestingModule
    -0.53
    POSITIVE LOGITS
     remember
    1.09
     think
    1.02
     recall
    0.84
    think
    0.83
     believe
    0.74
     suppose
    0.69
    Think
    0.69
     Think
    0.68
    Remember
    0.66
     Remember
    0.64
    Activations Density 0.231%

    No Known Activations