© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    specific technical or programming terminology

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

    Hexadecimal values and bit shifts

    np_acts-logits-general · gemini-2.0-flash

    carry out, relaxation times, bit more, structures behind

    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
    AnimationsModule
    -0.61
     يتيمه
    -0.49
    tagHelperRunner
    -0.49
    getDoctrine
    -0.47
    原始内容存档于
    -0.46
    OGND
    -0.45
    存于互联网档案馆
    -0.45
    esgue
    -0.45
    Referencie
    -0.44
     ProtoMessage
    -0.44
    POSITIVE LOGITS
     дописавши
    0.41
    sworth
    0.41
    ۇ
    0.40
     ped
    0.40
    erski
    0.39
    ires
    0.39
    StructEnd
    0.39
    tangentMode
    0.38
    inFile
    0.38
     onData
    0.38
    Activations Density 0.754%

    No Known Activations