© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical estimation and values associated with data analysis

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

    numerical digits and mathematical notation in scientific equations.

    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
    AddTagHelper
    -0.52
    "}")
    -0.50
     defaultstate
    -0.48
     haast
    -0.45
    jsxFileName
    -0.45
    chakra
    -0.43
    UserScript
    -0.43
    Parameterized
    -0.42
    Aiheesta
    -0.42
    TagMode
    -0.41
    POSITIVE LOGITS
     intStringLen
    0.49
    ècie
    0.46
    oneofs
    0.40
    weightedMode
    0.39
     activo
    0.38
    ције
    0.37
     ativo
    0.37
     kasarigan
    0.35
     aérienne
    0.34
    UrlResolution
    0.34
    Activations Density 0.339%

    No Known Activations