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. 24-GEMMASCOPE-RES-16K
    6. 8395
    Prev
    Next
    INDEX
    Explanations

    instances of significant governmental or organizational secrecy and actions related to space exploration

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

    space missions or space programs

    np_acts-logits-general · gemini-2.0-flash

    space missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     flattered
    -0.60
    WithMany
    -0.52
    ymce
    -0.52
    ộm
    -0.52
     Magistrate
    -0.52
     muualla
    -0.52
    oa̍t
    -0.50
     الحره
    -0.50
    Forex
    -0.49
     drowning
    -0.49
    POSITIVE LOGITS
     astronauts
    1.03
     mission
    1.00
     NASA
    0.97
     space
    0.95
     Space
    0.93
     astronaut
    0.90
     Mission
    0.89
     missions
    0.89
    Space
    0.87
    NASA
    0.83
    Activations Density 0.135%

    No Known Activations