© 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. 24-GEMMASCOPE-RES-16K
    11. 6134
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal preferences and opinions

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

    Beginning of sentences or clauses ("So", "Thus")

    np_acts-logits-general · gemini-2.0-flash

    conclusions or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.65
    RTLU
    -0.57
    sizeCache
    -0.52
     ostavi
    -0.52
     otomatig
    -0.51
     utafitiHapana
    -0.50
    StructEnd
    -0.50
    OCCURRED
    -0.50
    tagHelperRunner
    -0.49
    CppMethod
    -0.49
    POSITIVE LOGITS
    SourceChecksum
    0.56
     clearly
    0.47
     quite
    0.47
     Clearly
    0.44
    vably
    0.44
     Quite
    0.39
    Clearly
    0.38
     Pretty
    0.38
    Pretty
    0.36
     думаете
    0.36
    Activations Density 0.416%

    No Known Activations