© 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. 3806
    Prev
    Next
    INDEX
    Explanations

    terms related to processes in manufacturing and legal contexts

    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
     betweenstory
    -0.68
    RegistryLite
    -0.66
    ignty
    -0.62
     welcome
    -0.62
    ucchini
    -0.59
    jooq
    -0.58
    BufferException
    -0.58
    CodeAttribute
    -0.55
    kháu
    -0.55
     ostavi
    -0.54
    POSITIVE LOGITS
    ]")]
    0.68
    Rüyada
    0.60
    :][
    0.59
    expandindo
    0.55
    Dữ
    0.53
     BoxDecoration
    0.52
    curité
    0.52
    ?')
    0.52
    ﴿
    0.51
    Segue
    0.51
    Activations Density 1.832%

    No Known Activations