© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9779
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and request for data or materials

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

    Availability upon request

    np_acts-logits-general · gemini-2.0-flash

    available upon request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -1.19
    \{\\
    -0.96
    ]")]
    -0.91
    InjectAttribute
    -0.91
    awtextra
    -0.85
     transfieras
    -0.84
    AddHtmlAttribute
    -0.84
    /*
    -0.80
     nahilalakip
    -0.78
    WebElementEntity
    -0.78
    POSITIVE LOGITS
     request
    1.46
    request
    1.21
     upon
    1.16
     requests
    1.14
     Request
    1.11
     requested
    1.09
    Request
    1.06
     REQUEST
    1.05
     Requests
    0.99
    REQUEST
    0.98
    Activations Density 0.154%

    No Known Activations