© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1603
    Prev
    Next
    INDEX
    Explanations

    references to specific mathematical objects or constructs

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

    Mathematical vectors and vector notations

    np_acts-logits-general · gemini-2.0-flash

    vector representations

    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
     getItemId
    -0.59
    tagHelperRunner
    -0.54
     pleaſure
    -0.49
    ToDouble
    -0.49
    TabIndex
    -0.49
    parab
    -0.48
     EconPapers
    -0.47
    endphp
    -0.45
     Mathf
    -0.45
     smtplib
    -0.45
    POSITIVE LOGITS
     vector
    0.67
    向量
    0.54
     vectors
    0.54
     Vector
    0.54
    Vector
    0.54
    vector
    0.52
     вектор
    0.50
     VECTOR
    0.49
    vec
    0.48
     벡터
    0.48
    Activations Density 1.350%

    No Known Activations