© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9270
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases that refer to legal and procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.84
    ########.
    -0.84
    <bos>
    -0.80
    mybatisplus
    -0.72
    XmlAccessType
    -0.64
    ValueStyle
    -0.63
    expandindo
    -0.63
    ModelSerializer
    -0.62
     muualla
    -0.59
    تقاوى
    -0.59
    POSITIVE LOGITS
     ſome
    0.67
    InstanceState
    0.64
     Eſ
    0.64
     theſe
    0.64
     purpoſe
    0.61
     ſeveral
    0.59
     neceſſ
    0.58
     Efq
    0.58
     eſ
    0.58
     deſt
    0.58
    Activations Density 2.675%

    No Known Activations