© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 28633
    Prev
    Next
    INDEX
    Explanations

    references to software testing modules and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfYear
    -0.33
     Grecs
    -0.28
     kral
    -0.28
     life
    -0.27
    Number
    -0.27
    setX
    -0.26
     cuándo
    -0.25
     hear
    -0.25
     ouest
    -0.25
     Kral
    -0.24
    POSITIVE LOGITS
    TestingModule
    8.13
     TestBed
    1.45
    AnimationsModule
    1.39
    SpringBootTest
    1.32
    TestBed
    1.28
    NgModule
    1.26
     CreateTagHelper
    1.16
    ScopeManager
    1.16
    AddTagHelper
    1.06
     NgModule
    1.05
    Activations Density 0.000%

    No Known Activations