© 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. 2-GEMMASCOPE-RES-16K
    11. 8600
    Prev
    Next
    INDEX
    Explanations

    variables or parameters represented by N and n in equations or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajevo
    -0.55
    aktery
    -0.44
    gså
    -0.43
    ✭✭
    -0.42
    OCCURRED
    -0.41
    RTEE
    -0.41
    RefNanny
    -0.41
    RTDA
    -0.40
     TÜ
    -0.40
    Diweddarwch
    -0.40
    POSITIVE LOGITS
    N
    3.06
     N
    2.59
    getN
    1.62
    setN
    1.44
    Ｎ
    1.34
     ن
    1.23
    n
    1.20
    Ns
    1.13
    𝑁
    1.13
     n
    1.11
    Activations Density 0.294%

    No Known Activations