© 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. 3-GEMMASCOPE-RES-16K
    11. 1786
    Prev
    Next
    INDEX
    Explanations

    references to returning or revisiting places or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.38
    SequentialGroup
    -1.23
    Geplaatst
    -1.21
     Efq
    -1.16
     Roskov
    -1.15
    MigrationBuilder
    -1.13
     myſelf
    -1.13
    TagMode
    -1.12
     CreateTagHelper
    -1.11
    Portale
    -1.10
    POSITIVE LOGITS
     back
    0.78
    !
    0.74
     comeback
    0.74
    .
    0.72
     
    0.69
    -
    0.63
     to
    0.61
    ,
    0.61
     for
    0.59
     return
    0.58
    Activations Density 0.107%

    No Known Activations