© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3998
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that begin with "If" or refer to situations involving "you."

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

    "If" followed by "you"

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.46
     AssemblyProduct
    -0.40
    msn
    -0.38
    たびに
    -0.38
     ldc
    -0.37
    badlogic
    -0.37
     فر
    -0.36
     Gare
    -0.35
    UrlResolution
    -0.34
    WSER
    -0.34
    POSITIVE LOGITS
     yoksa
    0.63
     particulière
    0.62
     twij
    0.58
     unsure
    0.54
     indisponible
    0.54
     vôtre
    0.53
    AnchorStyles
    0.52
    どうしても
    0.52
     váš
    0.50
    hawatir
    0.49
    Activations Density 0.260%

    No Known Activations