© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 767
    Prev
    Next
    INDEX
    Explanations

    references to large quantities

    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
    abrigo
    -0.75
    ethene
    -0.74
     TextAppearance
    -0.72
    enumii
    -0.69
     nahilalakip
    -0.68
    Dichloro
    -0.66
    DockStyle
    -0.66
    authorised
    -0.65
    irable
    -0.65
     localObject
    -0.65
    POSITIVE LOGITS
     ton
    3.19
     tons
    2.83
     Tons
    2.57
     Ton
    2.42
     TON
    2.42
    Tons
    2.39
    Ton
    2.38
    ton
    2.18
     toneladas
    2.02
    tons
    2.02
    Activations Density 0.052%

    No Known Activations