© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7127
    Prev
    Next
    INDEX
    Explanations

    titles and introductory sections of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istoitu
    -0.89
    EndGlobalSection
    -0.79
    ::_('
    -0.74
    Personensuche
    -0.72
    webElementXpaths
    -0.71
    Gweler
    -0.70
    bewerken
    -0.67
    hoeddwyd
    -0.66
    enumi
    -0.65
    Sucesor
    -0.65
    POSITIVE LOGITS
    Description
    0.61
     Description
    0.60
    Overview
    0.59
    rašymas
    0.58
    OVERVIEW
    0.57
    Beskrivning
    0.57
    INTRODUCTION
    0.57
    beschreibung
    0.57
    Introduction
    0.56
     MonoBehaviour
    0.56
    Activations Density 0.217%

    No Known Activations