© 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. 22-GEMMASCOPE-RES-16K
    6. 14258
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "does" and its variations

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

    Comes before "not"

    np_acts-logits-general · gemini-2.0-flash

    do does did not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.70
    րջ
    -0.59
    forKey
    -0.58
    aucune
    -0.56
    Don
    -0.54
    evos
    -0.54
    argento
    -0.54
    readAs
    -0.52
     повіт
    -0.52
     "..\..\
    -0.52
    POSITIVE LOGITS
    Παραπομπές
    0.79
     المعيارى
    0.72
     intptr
    0.64
     consultato
    0.63
    ValueStyle
    0.62
    expandindo
    0.61
     وتسجيلات
    0.61
    הערות
    0.60
     not
    0.59
    ("")]
    
    0.59
    Activations Density 0.259%

    No Known Activations