© 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. 20-GEMMASCOPE-RES-16K
    11. 7896
    Prev
    Next
    INDEX
    Explanations

    words related to verification and confirmation processes

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

    Following "Za", "u", "ng", or "ved"

    np_acts-logits-general · gemini-2.0-flash

    "za" / "på" / "u" followed by specific words

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pleaſure
    -1.22
     houſe
    -1.22
     itſelf
    -1.21
     ſever
    -1.12
     myſelf
    -1.12
     ſta
    -1.12
     Houſe
    -1.09
     Reſ
    -1.07
     purpoſe
    -1.06
     Jefus
    -1.06
    POSITIVE LOGITS
     
    0.58
     “
    0.55
     u
    0.54
     S
    0.53
     mga
    0.52
     en
    0.51
     "
    0.51
     T
    0.51
     p
    0.50
     P
    0.50
    Activations Density 0.030%

    No Known Activations