© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10919
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly in JSON-like formats

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

    JSON array brackets and structural delimiters in data.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taktlose
    -0.33
     "..\..\..\
    -0.32
     PopupWindow
    -0.32
    Географиясе
    -0.31
    どちら
    -0.30
    ագրություններ
    -0.30
    staticmethod
    -0.29
    organ
    -0.29
     strtok
    -0.29
    FXMLLoader
    -0.29
    POSITIVE LOGITS
     ujednoznacz
    0.85
    Diweddarwch
    0.66
     հղումներ
    0.64
    tagPool
    0.63
     cherchés
    0.63
    Jîn
    0.60
    fjspx
    0.57
     ISNI
    0.56
    BeginContext
    0.54
    numerusform
    0.54
    Activations Density 1.617%

    No Known Activations