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. 8-GEMMASCOPE-RES-16K
    6. 4701
    Prev
    Next
    INDEX
    Explanations

    references to protocol buffer definitions and related structures

    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
    CultureInfo
    -0.84
    ValueGeneration
    -0.82
    WaitGroup
    -0.82
     endroits
    -0.81
    ModelAdmin
    -0.80
     gouttes
    -0.80
     gatto
    -0.79
    stdlib
    -0.78
    XtraGrid
    -0.78
    PCell
    -0.77
    POSITIVE LOGITS
     proto
    1.84
    proto
    1.82
     Proto
    1.80
    Proto
    1.67
    PROTO
    1.51
     prototypes
    1.44
     PROTO
    1.44
     prototype
    1.34
    Protos
    1.32
     prototyping
    1.20
    Activations Density 0.074%

    No Known Activations