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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 311
    Prev
    Next
    INDEX
    Explanations

    function calls and method invocations in code snippets

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

    Android context and builder methods

    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
    rungsseite
    -0.64
     disambiguazione
    -0.62
    leſs
    -0.55
    ſelf
    -0.50
     ſche
    -0.49
    swick
    -0.49
     المعيارى
    -0.48
     pleaſure
    -0.47
     arrest
    -0.46
     SPOT
    -0.46
    POSITIVE LOGITS
     resourceCulture
    0.49
    Хьажоргаш
    0.47
    webElementXpaths
    0.42
     PeEnEo
    0.41
     omgeving
    0.40
     potřeb
    0.38
     vrijwilli
    0.37
     ragazze
    0.37
     fallu
    0.36
     otomatig
    0.36
    Activations Density 0.002%

    No Known Activations