© 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. 18-GEMMASCOPE-RES-16K
    11. 3528
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and expressions of personal thoughts or feelings

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

    Following "I" or expressing certainty/assurance

    np_acts-logits-general · gemini-2.0-flash

    I can tell you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.73
     doInBackground
    -0.68
     AttributeSet
    -0.67
     StringTokenizer
    -0.64
    RegressionTest
    -0.61
    最快更新
    -0.58
    cino
    -0.57
    bleau
    -0.57
     biologically
    -0.57
    DeleteBehavior
    -0.55
    POSITIVE LOGITS
     скажу
    0.80
     assure
    0.78
     tell
    0.69
    assure
    0.68
    告诉你
    0.61
     decir
    0.61
     posso
    0.60
     assures
    0.59
    Ска
    0.59
     dizer
    0.59
    Activations Density 0.096%

    No Known Activations