© 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. 10929
    Prev
    Next
    INDEX
    Explanations

    terminology and descriptions related to mechanical and structural devices

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

    descriptions of mechanical devices or objects with parts that are connected, suspended, or attached to each other.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    новништво
    -0.47
     égard
    -0.47
    Viited
    -0.47
    WebElementEntity
    -0.47
    RegressionTest
    -0.46
     attributed
    -0.46
     kolik
    -0.46
     bertambah
    -0.45
    Diweddarwch
    -0.45
     contributed
    -0.45
    POSITIVE LOGITS
     faſt
    0.47
     purpoſe
    0.45
    ousand
    0.43
     houſe
    0.42
     ſta
    0.41
    ">//
    0.40
     minib
    0.40
    ſelf
    0.40
     Houſe
    0.39
    下载附件
    0.39
    Activations Density 0.738%

    No Known Activations