© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 45604
    Prev
    Next
    INDEX
    Explanations

    words related to the action of adding or including something

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

    add- followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IActionResult
    -0.66
    viewController
    -0.59
     deviceId
    -0.59
    stringValue
    -0.57
    istocene
    -0.56
     UnityEngine
    -0.56
    IActionResult
    -0.55
    controlador
    -0.54
    неопр
    -0.53
    BrowserModule
    -0.53
    POSITIVE LOGITS
     add
    1.52
     Add
    1.45
    add
    1.41
    Add
    1.39
     adds
    1.16
    ADD
    1.13
     Adds
    1.11
     ADD
    1.09
    adds
    1.06
    Adds
    1.04
    Activations Density 0.039%

    No Known Activations