© 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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5746
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states typically associated with confusion, sadness, or self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.04
     smtplib
    -0.82
    ^(@)
    -0.80
     Majefty
    -0.77
     ſtate
    -0.76
     againſt
    -0.76
     ſmall
    -0.74
    ſelves
    -0.73
    存于互联网档案馆
    -0.72
     $_"
    -0.71
    POSITIVE LOGITS
     am
    0.80
     Am
    0.71
    am
    0.66
     was
    0.60
    Am
    0.57
    testify
    0.55
     myself
    0.54
     بودم
    0.54
    richTextPanel
    0.54
     A
    0.53
    Activations Density 0.164%

    No Known Activations