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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5838
    Prev
    Next
    INDEX
    Explanations

    sections of text that provide descriptions or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ioutil
    -0.48
    oredCriteria
    -0.47
    脚注の使い方
    -0.45
     Greeley
    -0.45
     transférez
    -0.44
     cerebellum
    -0.44
     juſt
    -0.44
     preſent
    -0.44
    stylers
    -0.43
     UIKit
    -0.43
    POSITIVE LOGITS
    符
    0.46
     singkat
    0.43
     DETAIL
    0.43
    Aholisi
    0.42
     sensazione
    0.42
     Wicidata
    0.40
     détaillée
    0.38
    addContainerGap
    0.36
     briefly
    0.36
    NameInMap
    0.35
    Activations Density 0.129%

    No Known Activations