© 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. 23-GEMMASCOPE-RES-16K
    11. 9553
    Prev
    Next
    INDEX
    Explanations

    medical terminology and references to methods or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erçe
    -0.49
    twimg
    -0.47
    suddenly
    -0.45
     hacerte
    -0.45
    oxyd
    -0.45
    webElementGuid
    -0.45
    official
    -0.44
    attitude
    -0.43
    intenant
    -0.42
    banded
    -0.42
    POSITIVE LOGITS
    Abstract
    0.57
     research
    0.52
    期刊论文
    0.51
    Keywords
    0.51
     Abstract
    0.49
     researchers
    0.46
     연구
    0.44
    DOI
    0.43
     Research
    0.42
     experimental
    0.42
    Activations Density 2.118%

    No Known Activations