© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9525
    Prev
    Next
    INDEX
    Explanations

    elements related to user interactions and characteristics within various contexts

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

    Reference to a person, role, or user

    np_acts-logits-general · gemini-2.0-flash

    person or user roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grandsons
    -0.62
     uncles
    -0.59
     serai
    -0.57
     fathers
    -0.57
    íritu
    -0.56
     defraud
    -0.55
     Guys
    -0.55
     Sons
    -0.53
     mothers
    -0.52
     hombres
    -0.51
    POSITIVE LOGITS
     person
    1.03
     pessoa
    0.88
     osoba
    0.85
     PERSON
    0.82
     Person
    0.78
     who
    0.77
    person
    0.76
    Person
    0.72
     quien
    0.68
     iemand
    0.67
    Activations Density 0.519%

    No Known Activations