© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8803
    Prev
    Next
    INDEX
    Explanations

    references to a process or action related to file manipulation or delivery

    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
     fortnite
    -0.52
    createCell
    -0.52
    AddTagHelper
    -0.51
    fortnite
    -0.49
     createSprite
    -0.49
    ！");
    -0.47
     alongside
    -0.47
    RunWith
    -0.47
     ${({
    -0.46
     endregion
    -0.46
    POSITIVE LOGITS
    >
    0.90
    ...>
    0.81
     >
    0.81
     wrote
    0.80
     schrieb
    0.79
    :>
    0.79
    ...@
    0.75
    >>
    0.74
    wrote
    0.73
    ]>
    0.72
    Activations Density 0.885%

    No Known Activations