© 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. 11-GEMMASCOPE-RES-16K
    11. 5546
    Prev
    Next
    INDEX
    Explanations

    technical terminology and references in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecio
    -0.52
    telli
    -0.49
     rembour
    -0.49
     Balak
    -0.48
    geleitet
    -0.48
     Aitken
    -0.48
    isio
    -0.47
    arela
    -0.47
     other
    -0.46
     Pedersen
    -0.46
    POSITIVE LOGITS
    horabuena
    0.72
    Tracce
    0.56
    uxxxx
    0.56
    Portale
    0.54
     transfieras
    0.52
    webElementXpaths
    0.52
     disambiguazione
    0.52
     Wirt
    0.52
    BeanUtils
    0.50
    Ⅲ
    0.49
    Activations Density 3.420%

    No Known Activations