© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 6797
    Prev
    Next
    INDEX
    Explanations

    URLs and associated web resource indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs and web addresses

    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
    othelioma
    -0.51
    romyalgia
    -0.42
     Wounds
    -0.41
     Sharpe
    -0.41
    MenuInflater
    -0.41
     Rag
    -0.41
     repul
    -0.41
     rez
    -0.40
     brun
    -0.40
    theid
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.62
     Weibo
    0.60
    elong
    0.59
     yyl
    0.57
    aliyun
    0.54
    FontOfSize
    0.54
     WeChat
    0.54
    OGND
    0.54
    sina
    0.54
    mall
    0.53
    Activations Density 0.205%

    No Known Activations