Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1208
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to functions and promises

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

    javascript promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.52
    SharedDtor
    -0.46
     ComVisible
    -0.43
    Aktualisiert
    -0.42
    :"-"`
    -0.41
    noinspection
    -0.41
     CURIAM
    -0.41
    ništvo
    -0.40
     հղումներ
    -0.40
     recevrez
    -0.40
    POSITIVE LOGITS
     promises
    0.54
    oa̍t
    0.50
    Promise
    0.50
     promise
    0.49
    tagHelperRunner
    0.47
     Мексичка
    0.46
    SequentialGroup
    0.44
    Promises
    0.44
     flock
    0.43
     Promises
    0.43
    Activations Density 0.044%

    No Known Activations