© 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. 25-GEMMASCOPE-RES-16K
    11. 14581
    Prev
    Next
    INDEX
    Explanations

    references to specific studies or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     […]
    -2.37
     ...
    -2.35
     …
    -2.19
    ...
    -2.10
     [...]
    -2.06
    ,...
    -2.02
     ..."
    -1.94
    […]
    -1.90
    …
    -1.84
    .…
    -1.81
    POSITIVE LOGITS
    <sub>
    0.93
    <sup>
    0.91
    <em>
    0.81
    <u>
    0.72
    =("
    0.61
    <code>
    0.60
    <i>
    0.59
     ($\
    0.59
    $^{-
    0.59
     {@
    0.57
    Activations Density 1.300%

    No Known Activations