© 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. 0-GEMMASCOPE-RES-16K
    11. 7353
    Prev
    Next
    INDEX
    Explanations

    references to shapes and data structure terms used in programming or data manipulation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onedDateTime
    -0.59
    strix
    -0.53
     BIBSYS
    -0.49
     himſelf
    -0.49
    rema
    -0.49
     sidan
    -0.48
     themſelves
    -0.48
    Pratique
    -0.48
     RIPRODUZIONE
    -0.47
    회
    -0.47
    POSITIVE LOGITS
    shape
    0.96
     nahilalakip
    0.89
     pinulongan
    0.81
     Gran
    0.80
    Gran
    0.78
    ParallelGroup
    0.76
    цездатний
    0.68
     Grant
    0.67
    GRAN
    0.67
     مرئيه
    0.65
    Activations Density 0.145%

    No Known Activations