© 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. 4241
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations involving indices

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

    "i" followed by ordinal suffixes

    np_acts-logits-general · gemini-2.0-flash

    referring to i-th items

    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
    IUrlHelper
    -0.78
    Становништво
    -0.47
     الرياضيه
    -0.45
     beginnetje
    -0.44
    TypedDataSet
    -0.42
    ViewFeatures
    -0.40
    StructEnd
    -0.39
    ंदीखरीदारी
    -0.39
    ErrUnexpectedEOF
    -0.36
    StandardCharsets
    -0.36
    POSITIVE LOGITS
    th
    0.87
    第
    0.83
     fifth
    0.82
     sixth
    0.81
     ninth
    0.81
     seventh
    0.81
    nth
    0.78
     fourth
    0.77
     tenth
    0.76
    ième
    0.72
    Activations Density 0.321%

    No Known Activations