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. 4606
    Prev
    Next
    INDEX
    Explanations

    greetings and expressions of sentiment in communication

    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
    FieldDescriptor
    -1.01
    DockStyle
    -0.92
    WithIOException
    -0.88
    ViewFeatures
    -0.84
    oplayer
    -0.82
    UserScript
    -0.81
    tagHelperRunner
    -0.80
     famí
    -0.80
     يتيمه
    -0.79
     متعلقه
    -0.79
    POSITIVE LOGITS
     Hira
    0.99
     Hiram
    0.84
     HIR
    0.76
    hi
    0.75
     Hir
    0.75
    erals
    0.74
     Hi
    0.73
     lolita
    0.72
     hir
    0.70
     hi
    0.70
    Activations Density 0.106%

    No Known Activations