© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15563
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to specific occurrences or entities in a formal context, such as legal references and findings

    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
    AccessorTable
    -0.64
    Personendaten
    -0.60
    FormTagHelper
    -0.58
    SerializedName
    -0.58
    yntaxException
    -0.57
    Diweddarwch
    -0.56
    tagHelperRunner
    -0.53
    UnsafeEnabled
    -0.52
    Билгалдахарш
    -0.51
    PropertyChanging
    -0.51
    POSITIVE LOGITS
     fifth
    3.00
     fourth
    2.96
     sixth
    2.92
     seventh
    2.89
     third
    2.82
     ninth
    2.81
     eighth
    2.75
     tenth
    2.58
    fifth
    2.50
    fourth
    2.49
    Activations Density 0.731%

    No Known Activations