© 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. 21-GEMMASCOPE-RES-16K
    11. 14866
    Prev
    Next
    INDEX
    Explanations

    references to online platforms and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.74
    PreferredItem
    -0.67
    ngdoc
    -0.64
    addCriterion
    -0.63
    LookAnd
    -0.62
    utilisons
    -0.62
    ContentAsync
    -0.61
     PyLong
    -0.61
     AssemblyTitle
    -0.61
    ')")
    -0.60
    POSITIVE LOGITS
    com
    1.44
     com
    1.32
    Com
    1.07
     Com
    0.96
    COM
    0.92
     org
    0.82
    org
    0.80
     dot
    0.79
    .
    0.78
     COM
    0.77
    Activations Density 0.178%

    No Known Activations