© 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. 25-GEMMASCOPE-RES-16K
    6. 12299
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kun
    -0.68
     Kir
    -0.63
     esternos
    -0.63
     Kernel
    -0.62
     Keyword
    -0.61
     Ke
    -0.60
     незавершена
    -0.59
     Kent
    -0.58
     Kettle
    -0.58
     Key
    -0.55
    POSITIVE LOGITS
     k
    2.37
    k
    2.23
    k
    1.04
     к
    0.99
    𝑘
    0.96
    к
    0.93
    𝗸
    0.87
    kkkk
    0.82
    kA
    0.82
    𝙠
    0.81
    Activations Density 0.923%

    No Known Activations