© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5512
    Prev
    Next
    INDEX
    Explanations

    references to actual locations, verbs related to visibility or transparency, and indicators of false or misleading information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Stand
    -0.59
    strip
    -0.54
     Strip
    -0.50
     Stand
    -0.50
    Strip
    -0.50
     strip
    -0.50
     Strand
    -0.50
    Strand
    -0.49
     Strike
    -0.48
     Standard
    -0.47
    POSITIVE LOGITS
     stars
    0.72
     statements
    0.71
     stats
    0.70
     statutes
    0.65
     stares
    0.65
     stocks
    0.63
     steaks
    0.61
     steels
    0.60
     stamens
    0.60
     strawberries
    0.58
    Activations Density 0.481%

    No Known Activations