© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7489
    Prev
    Next
    INDEX
    Explanations

    references to people and their relationships, as well as claims in legal contexts

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

    Followed by "must" or a similar word

    np_acts-logits-general · gemini-2.0-flash

    must obligation necessity

    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
    twimg
    -0.54
     AssemblyCulture
    -0.50
    الحياه
    -0.50
     nahilalakip
    -0.47
    +#+#
    -0.47
    alyptus
    -0.44
     otomatig
    -0.44
    Personensuche
    -0.43
     esternos
    -0.43
    #+#
    -0.43
    POSITIVE LOGITS
     must
    0.82
    must
    0.61
     müssen
    0.61
     Must
    0.56
     musst
    0.54
     doivent
    0.52
     MUST
    0.52
     moeten
    0.51
     måste
    0.51
    ต้อง
    0.49
    Activations Density 0.284%

    No Known Activations