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. 8-GEMMASCOPE-RES-16K
    6. 5103
    Prev
    Next
    INDEX
    Explanations

    references to planets and extraterrestrial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viață
    -0.65
     musikk
    -0.65
    edith
    -0.64
     păr
    -0.64
    +#+
    -0.63
    a
    -0.63
    dollis
    -0.62
     CreateTagHelper
    -0.62
     kysy
    -0.62
     Alla
    -0.61
    POSITIVE LOGITS
     Planet
    1.25
     robots
    1.22
     robot
    1.22
     planet
    1.20
     PLANET
    1.15
     Robot
    1.14
    Robots
    1.12
     Robots
    1.12
     planets
    1.07
    planet
    1.07
    Activations Density 0.099%

    No Known Activations