© 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. 10-GEMMASCOPE-RES-16K
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    terms related to data access and structural attributes in a computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ğunu
    -0.51
    他自己
    -0.51
    izarse
    -0.48
     trovar
    -0.47
     Audiodateien
    -0.47
     fVar
    -0.47
     izin
    -0.44
     dicendo
    -0.44
    SOUNDBITE
    -0.44
    binar
    -0.44
    POSITIVE LOGITS
     myſelf
    0.90
     poffible
    0.80
     pleaſure
    0.77
     ſmall
    0.72
     againſt
    0.72
     whoſe
    0.71
    ̈́
    0.71
     themſelves
    0.71
     faſt
    0.69
     purpoſe
    0.68
    Activations Density 1.044%

    No Known Activations