© 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. 14-GEMMASCOPE-RES-16K
    11. 7860
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate governance and financial accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telefónica
    -0.47
     kaarangay
    -0.46
    Jereo
    -0.45
    mtrl
    -0.44
     prochaine
    -0.43
    |};
    -0.42
    rillation
    -0.40
    yyj
    -0.39
    mientos
    -0.39
     secular
    -0.39
    POSITIVE LOGITS
     الحره
    0.47
     auto
    0.46
    twimg
    0.45
    Personendaten
    0.44
    ContentAlignment
    0.44
    #+#
    0.43
     nonUne
    0.42
     CEO
    0.40
    ButterKnife
    0.39
    脚注の使い方
    0.39
    Activations Density 0.357%

    No Known Activations