© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9373
    Prev
    Next
    INDEX
    Explanations

    terms related to cross-national and interdisciplinary collaboration in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.37
     Segurança
    -0.36
    Sentiment
    -0.34
     Sahib
    -0.34
     titulares
    -0.34
    GetInstance
    -0.34
    Liberal
    -0.34
     beliau
    -0.33
    dafx
    -0.33
    ┆
    -0.33
    POSITIVE LOGITS
     cross
    1.39
    cross
    1.28
    Cross
    1.25
     Cross
    1.25
     CROSS
    1.20
    CROSS
    1.12
     crosses
    1.05
     crossing
    1.02
     cros
    0.96
    crossing
    0.91
    Activations Density 0.124%

    No Known Activations