© 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. 30-GEMMASCOPE-RES-16K
    11. 13897
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and formatting related to mathematical expressions

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

    LaTeX code

    np_acts-logits-general · gemini-2.0-flash

    parameters, transformations, rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.66
    بوابة
    -0.56
    mybatisplus
    -0.56
     utafitiHapana
    -0.54
     متعلقه
    -0.52
    TabIndex
    -0.52
    原始内容存档于
    -0.51
    mings
    -0.49
    Naissance
    -0.49
    jbl
    -0.48
    POSITIVE LOGITS
    fromnode
    0.45
     iprot
    0.41
     critical
    0.37
    危险
    0.37
    危險
    0.37
    ulico
    0.32
     compless
    0.31
     cond
    0.30
     Bewußt
    0.30
     srebr
    0.29
    Activations Density 0.057%

    No Known Activations