© 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. 2-GEMMASCOPE-RES-16K
    6. 948
    Prev
    Next
    INDEX
    Explanations

    expressions related to changes in states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useRouter
    -0.59
    RectangleBorder
    -0.58
     xoay
    -0.55
     GTS
    -0.55
    一邊
    -0.54
    Alma
    -0.54
     Pico
    -0.54
    issau
    -0.53
     Hiz
    -0.53
     Arche
    -0.53
    POSITIVE LOGITS
    了
    2.63
     了
    1.98
    了我
    1.34
    了你
    1.32
    了他
    1.27
    了她
    1.26
    了一
    1.25
    了自己
    1.14
    了的
    1.12
    了他的
    1.05
    Activations Density 0.022%

    No Known Activations