Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 443
    Prev
    Next
    INDEX
    Explanations

    phrases related to affirmative action and higher education

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

    Attended [School Name]

    np_acts-logits-general · gemini-2.0-flash

    universities, colleges, and academic 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
    InSection
    -0.54
     getan
    -0.48
     Blackpool
    -0.43
    maxcdn
    -0.41
     kaban
    -0.40
     municipales
    -0.40
     empres
    -0.39
     fosse
    -0.39
     Madsen
    -0.38
     surpre
    -0.38
    POSITIVE LOGITS
    ElementException
    0.92
    Vidite
    0.87
    uride
    0.83
    OGND
    0.81
    oredCriteria
    0.81
    webElement
    0.78
    GEBURTSDATUM
    0.76
     Yale
    0.76
     LoginComponent
    0.75
    الدراسه
    0.75
    Activations Density 0.267%

    No Known Activations