© 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. 15487
    Prev
    Next
    INDEX
    Explanations

    parts of the text that are empty or contain no significant content

    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
     tartalomajánló
    -0.80
    HasForeignKey
    -0.72
    AsUp
    -0.67
    optionalTypeArgs
    -0.60
     مفص
    -0.60
    ItemBackground
    -0.60
    Precautionary
    -0.57
     Italijanski
    -0.57
    Vidite
    -0.56
    )_/¯
    -0.56
    POSITIVE LOGITS
    CodeAttribute
    0.71
    CodeDom
    0.62
    DebuggerNonUser
    0.56
     cycl
    0.54
    CompilerServices
    0.51
     code
    0.51
     hinweg
    0.50
    存于互联网档案馆
    0.49
    UnitTesting
    0.49
    #
    0.48
    Activations Density 0.011%

    No Known Activations