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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3153
    Prev
    Next
    INDEX
    Explanations

    references to stable systems and processes in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hotra
    -0.53
    erski
    -0.51
     Chiu
    -0.50
    èlement
    -0.50
    ifax
    -0.48
     Gunter
    -0.48
     primary
    -0.48
     cancers
    -0.48
    iroz
    -0.47
     Bunting
    -0.47
    POSITIVE LOGITS
     estekak
    0.89
    wpi
    0.87
    providedIn
    0.80
     rospy
    0.78
    脚注の使い方
    0.76
    MLLoader
    0.75
     "..\..\..\
    0.75
    internalType
    0.75
    nestjs
    0.73
     بيها
    0.73
    Activations Density 0.830%

    No Known Activations