© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5263
    Prev
    Next
    INDEX
    Explanations

    terms related to documentation and recording information

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

    Official and historical records/reports

    np_acts-logits-general · gemini-2.0-flash

    official records and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.40
     Türkei
    -0.39
     geométrico
    -0.39
     âgées
    -0.38
    utriche
    -0.38
    Према
    -0.38
     elegido
    -0.37
     teoría
    -0.37
    élaboration
    -0.37
     convocatoria
    -0.37
    POSITIVE LOGITS
     record
    0.59
     recorded
    0.57
    record
    0.49
     registered
    0.49
    memoized
    0.48
    recorded
    0.48
     Codable
    0.48
     recording
    0.47
    Recorded
    0.47
     Record
    0.47
    Activations Density 0.558%

    No Known Activations