© 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. 6462
    Prev
    Next
    INDEX
    Explanations

    instances of the word "another" and variations indicating repetition or addition

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

    Appearing after "another" or "second"

    np_acts-logits-general · gemini-2.0-flash

    another number or group

    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
    tagHelperRunner
    -0.64
    SequentialGroup
    -0.60
    CloseOperation
    -0.55
    IContainer
    -0.52
    Rohy
    -0.51
     retval
    -0.50
    dafx
    -0.50
    AppMethodBeat
    -0.49
    reordered
    -0.48
     jLabel
    -0.47
    POSITIVE LOGITS
     corrientes
    0.45
     Männern
    0.40
     doccia
    0.39
     Darauf
    0.38
     Erwachsenen
    0.37
     tenisky
    0.36
     damska
    0.36
     ejecutivo
    0.36
     Vertra
    0.34
     같은
    0.34
    Activations Density 0.564%

    No Known Activations