Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2658
    Prev
    Next
    INDEX
    Explanations

    references to the moon or lunar phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppCompatTheme
    -0.52
    EndProject
    -0.45
    CodeAttribute
    -0.44
    niſſe
    -0.44
     dieſem
    -0.43
     AssemblyCulture
    -0.43
    ſchaft
    -0.43
    titch
    -0.43
    cerpt
    -0.42
    geschenk
    -0.42
    POSITIVE LOGITS
     moon
    0.83
     rain
    0.69
    moon
    0.69
     Moon
    0.67
     Rain
    0.63
    Rain
    0.60
     MOON
    0.60
    qu
    0.60
     RAIN
    0.57
    Moon
    0.55
    Activations Density 0.194%

    No Known Activations