© 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. 2-GEMMASCOPE-RES-16K
    11. 8743
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to biomedical and health research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MutableLiveData
    -0.50
     gezet
    -0.48
    +#+#
    -0.45
     مشين
    -0.44
     receitas
    -0.43
    símbolo
    -0.40
    WriteBarrier
    -0.38
    脚注の使い方
    -0.37
     nahilalakip
    -0.37
    reporting
    -0.37
    POSITIVE LOGITS
     thy
    0.65
    dd
    0.57
     resourceCulture
    0.56
     compression
    0.56
     Thy
    0.55
    ə
    0.55
    InjectAttribute
    0.55
     lease
    0.54
     compress
    0.54
    thy
    0.54
    Activations Density 0.594%

    No Known Activations