© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5341
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions and the usage of the verb "to be."

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

    Auxiliary verb before a verb

    np_acts-logits-general · gemini-2.0-flash

    auxiliary + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.68
    featureID
    -0.64
    tly
    -0.61
    IsContent
    -0.60
     noft
    -0.60
     drapeau
    -0.59
     Agamemnon
    -0.59
     périph
    -0.58
     referenties
    -0.56
    ologically
    -0.55
    POSITIVE LOGITS
     '\\;'
    0.62
     مرئيه
    0.54
     happen
    0.53
     فريبيس
    0.52
    ']))
    
    0.51
    VAO
    0.50
    قایناق‌لار
    0.49
    ConstraintLayout
    0.49
    enido
    0.49
    inflater
    0.48
    Activations Density 0.606%

    No Known Activations