© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11375
    Prev
    Next
    INDEX
    Explanations

    strongly emphasized necessity or obligation in statements

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

    "Must" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    must followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     afield
    -0.48
    StatusOK
    -0.42
     Schie
    -0.40
    orien
    -0.40
    idea
    -0.40
     oras
    -0.40
     leyendo
    -0.40
    eaway
    -0.40
     العام
    -0.40
    ⓧ
    -0.39
    POSITIVE LOGITS
     Must
    1.34
     must
    1.34
    Must
    1.21
    must
    1.16
     MUST
    1.16
    MUST
    1.07
     harus
    0.85
     mustn
    0.82
     doit
    0.80
     doivent
    0.78
    Activations Density 0.044%

    No Known Activations