© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8118
    Prev
    Next
    INDEX
    Explanations

    percentage signs and comments that indicate steps or procedures in code

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

    Code comments or code-related formatting

    np_acts-logits-general · gemini-2.0-flash

    code comments and structure starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.46
    ientôt
    -0.37
    ="@+
    -0.37
    Across
    -0.35
     StatelessWidget
    -0.35
    heça
    -0.35
    UrlResolution
    -0.35
    发表于
    -0.34
    <?
    -0.34
    PyExc
    -0.34
    POSITIVE LOGITS
     check
    0.66
     obtain
    0.64
     calculate
    0.61
     retrieve
    0.61
     attempt
    0.59
     prepare
    0.59
     establish
    0.59
     determine
    0.58
     collect
    0.57
     update
    0.57
    Activations Density 0.382%

    No Known Activations