© 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. 31-GEMMASCOPE-RES-16K
    11. 684
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements or figures related to materials or waste

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

    medical terminology in text, particularly focusing on anatomical and clinical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    medical and anatomical terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -1.05
    XmlAccessType
    -0.69
     Приступљено
    -0.59
     Roskov
    -0.57
    *}[
    -0.56
    }`}
    -0.56
     }{@
    -0.55
    ]};
    -0.54
    )}^{
    -0.53
     BoxFit
    -0.53
    POSITIVE LOGITS
     őket
    0.37
     kysy
    0.35
    unnitel
    0.35
    importanza
    0.34
    umumkan
    0.34
     createState
    0.34
     afectado
    0.34
    gyű
    0.33
     ſein
    0.33
     magát
    0.33
    Activations Density 0.186%

    No Known Activations