© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 76663
    Prev
    Next
    INDEX
    Explanations

    occurrences of JavaScript-related content in the document

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

    JavaScript files and libraries

    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
     Tiefe
    -0.52
    FilterChain
    -0.45
    mybatisplus
    -0.45
    CodedInputStream
    -0.44
    abstractmethod
    -0.43
     Glance
    -0.42
     Mühe
    -0.42
    mido
    -0.41
    afficheront
    -0.41
    めでとう
    -0.41
    POSITIVE LOGITS
     js
    1.17
     JS
    1.09
    js
    1.04
    JS
    0.87
     JavaScript
    0.78
     javascript
    0.78
     Js
    0.75
    javascript
    0.74
    JavaScript
    0.72
     Javascript
    0.71
    Activations Density 0.012%

    No Known Activations