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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15084
    Prev
    Next
    INDEX
    Explanations

    references to software components and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     halus
    -0.57
    IonicModule
    -0.55
    yaszt
    -0.53
    IUrlHelper
    -0.52
     aktif
    -0.50
    blocking
    -0.50
     Cuer
    -0.50
    — 
    -0.50
    헌
    -0.50
    volunteer
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.88
    emf
    0.73
    الحياه
    0.69
     '{@
    0.68
     EClass
    0.66
    >{@
    0.62
     snippetHide
    0.61
    featureID
    0.60
    "}";
    0.59
    Personendaten
    0.58
    Activations Density 0.034%

    No Known Activations