© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 9808
    Prev
    Next
    INDEX
    Explanations

    references to organizations, investigations, or processes related to health and competition in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сылкі
    -0.62
     gynhyrchwyd
    -0.61
    RectangleBorder
    -0.55
    MethodManager
    -0.54
     oprot
    -0.52
     BoxDecoration
    -0.51
     MainAxisSize
    -0.50
    DrawerLayout
    -0.49
     bezeichneter
    -0.48
    adpleegd
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.72
     चीज़ों
    0.60
    kema
    0.56
    geable
    0.55
    terer
    0.53
    SerializedSize
    0.53
    BOLD
    0.52
     noce
    0.52
    Rujuakan
    0.51
    itier
    0.51
    Activations Density 1.842%

    No Known Activations