© 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. 20-GEMMASCOPE-RES-16K
    11. 2415
    Prev
    Next
    INDEX
    Explanations

    references to zodiac signs and their attributes

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

    zodiac signs and associated personality traits.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.82
    verwijspagina
    -0.69
    BufferException
    -0.62
     esternos
    -0.62
     ब्रेकडाउन
    -0.59
    WebElementEntity
    -0.57
    rungsseite
    -0.55
    ppuden
    -0.53
    majánló
    -0.52
    ंदीखरीदारी
    -0.51
    POSITIVE LOGITS
     tend
    0.40
     costuma
    0.40
    zule
    0.40
     scopri
    0.38
    RTEX
    0.38
     tends
    0.37
     Stur
    0.36
    BST
    0.36
     often
    0.36
    rari
    0.36
    Activations Density 0.048%

    No Known Activations