© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93067
    Prev
    Next
    INDEX
    Explanations

    references to students and their characteristics or experiences

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

    student variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    convite
    -0.61
     vorige
    -0.56
     laço
    -0.54
     aberta
    -0.52
     geral
    -0.51
     morire
    -0.51
     mijne
    -0.50
     legais
    -0.50
     direta
    -0.50
     feitos
    -0.49
    POSITIVE LOGITS
    Student
    1.24
     Students
    1.16
     Student
    1.16
    Students
    1.12
    student
    1.05
     student
    1.02
     students
    1.01
    students
    0.99
     STUDENT
    0.95
     STUDENTS
    0.94
    Activations Density 0.014%

    No Known Activations