© 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. 4-GEMMASCOPE-RES-16K
    11. 9950
    Prev
    Next
    INDEX
    Explanations

    references to figures or supplementary materials in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $}}
    -0.50
     
    -0.49
    gulier
    -0.46
    Adverten
    -0.41
     den
    -0.39
     Great
    -0.39
    4
    -0.39
     med
    -0.38
     Ross
    -0.37
    glected
    -0.37
    POSITIVE LOGITS
    脚注の使い方
    0.95
     autorytatywna
    0.90
     CreateTagHelper
    0.89
     ComVisible
    0.88
     Picchu
    0.86
     betweenstory
    0.84
    DotNetBar
    0.82
    PreferredItem
    0.82
    +#+
    0.82
    CloseOperation
    0.80
    Activations Density 0.707%

    No Known Activations