© 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. 5-GEMMASCOPE-RES-16K
    6. 6583
    Prev
    Next
    INDEX
    Explanations

    references to the concept of purity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.88
    omitempty
    -0.81
    knex
    -0.81
     насељу
    -0.80
    ngdoc
    -0.80
    LabelTagHelper
    -0.76
     Eisenhower
    -0.75
     Monfieur
    -0.75
    GHIJKLM
    -0.75
     Walkover
    -0.73
    POSITIVE LOGITS
     pure
    2.64
     Pure
    2.56
    pure
    2.50
    Pure
    2.42
     PURE
    2.31
    PURE
    2.12
     murni
    1.76
    纯
    1.71
     purest
    1.68
     puro
    1.66
    Activations Density 0.112%

    No Known Activations