© 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. 8-GEMMASCOPE-RES-16K
    11. 15206
    Prev
    Next
    INDEX
    Explanations

    instances of error codes in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -1.02
    PreferredItem
    -1.00
     poffe
    -0.91
     Efq
    -0.89
    principalColumn
    -0.89
     oprot
    -0.88
    WindowConstants
    -0.87
     ་་
    -0.86
     Monfieur
    -0.86
     ―――――
    -0.86
    POSITIVE LOGITS
     if
    0.63
    if
    0.58
     (
    0.51
     lo
    0.50
    !!!
    0.50
     If
    0.50
    怪
    0.49
    ICY
    0.49
    czek
    0.48
     all
    0.48
    Activations Density 0.064%

    No Known Activations