© 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. 15-GEMMASCOPE-RES-16K
    11. 5402
    Prev
    Next
    INDEX
    Explanations

    negative values or indications of loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -1.28
     CreateTagHelper
    -1.21
     متعلقه
    -1.18
     مشين
    -1.13
     nahilalakip
    -1.09
    UnusedPrivate
    -1.09
     myſelf
    -1.06
    expandindo
    -1.03
     Anſ
    -1.02
     Roskov
    -1.02
    POSITIVE LOGITS
     
    0.83
     '
    0.60
    ↵
    0.59
    ↵↵
    0.58
     [
    0.57
     $\
    0.57
     "
    0.55
     General
    0.51
    ()[
    0.51
     general
    0.50
    Activations Density 0.046%

    No Known Activations