© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27739
    Prev
    Next
    INDEX
    Explanations

    structured information about events and gatherings

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

    someone or somebody

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    WillAppear
    -0.58
    bekistan
    -0.55
    miento
    -0.54
    ंदीखरीदारी
    -0.53
    riceps
    -0.51
     باخ
    -0.50
    DOCTYPE
    -0.49
    üstü
    -0.49
     teneur
    -0.48
    gráfica
    -0.48
    POSITIVE LOGITS
     someone
    1.06
    someone
    1.01
     somebody
    0.98
    somebody
    0.98
     Someone
    0.98
    Someone
    0.96
     SOMEONE
    0.90
    Somebody
    0.86
     Somebody
    0.84
    Alguien
    0.80
    Activations Density 0.311%

    No Known Activations