© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8168
    Prev
    Next
    INDEX
    Explanations

    negations and phrases that challenge assertions or beliefs

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

    "Did" or "did" at the beginning of clauses/sentences

    np_acts-logits-general · gemini-2.0-flash

    detecting did and did not

    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
    currently
    -0.49
     Houſe
    -0.47
    rungsseite
    -0.47
    IntoConstraints
    -0.47
     currently
    -0.46
     now
    -0.45
     désormais
    -0.45
    ContentValues
    -0.45
     houſe
    -0.45
     actuellement
    -0.44
    POSITIVE LOGITS
     Did
    0.68
    did
    0.66
    Did
    0.64
    DID
    0.59
     did
    0.59
     previously
    0.58
     DID
    0.56
     recently
    0.55
     originally
    0.54
    recently
    0.53
    Activations Density 0.086%

    No Known Activations