© 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. 2-GEMMASCOPE-RES-16K
    11. 14888
    Prev
    Next
    INDEX
    Explanations

    tokens that represent various currency symbols or currency-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شة
    -0.48
     colspan
    -0.44
     Eſ
    -0.43
    artigen
    -0.43
    pravy
    -0.42
    esome
    -0.42
     ritard
    -0.41
    Sensitive
    -0.40
     Sensitive
    -0.40
     rezept
    -0.40
    POSITIVE LOGITS
    AnchorStyles
    1.02
    iastes
    0.77
    AndEndTag
    0.76
     onBind
    0.75
    mybatisplus
    0.74
    WriteTagHelper
    0.73
     betweenstory
    0.72
     оригіналу
    0.72
    VIAF
    0.71
    +:+
    0.71
    Activations Density 0.292%

    No Known Activations