© 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. 11-GEMMASCOPE-RES-16K
    6. 4687
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to absorption processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patil
    -0.66
     brady
    -0.61
     Field
    -0.59
     Fields
    -0.59
     field
    -0.58
     trigo
    -0.57
    k
    -0.57
    T
    -0.57
     Jolie
    -0.57
    ẵn
    -0.56
    POSITIVE LOGITS
     Absor
    1.64
    absorbed
    1.62
     absorb
    1.58
     absorbs
    1.55
    Absor
    1.51
     absorption
    1.50
     absorbing
    1.50
     absorbed
    1.48
     Absorption
    1.48
     Absorb
    1.43
    Activations Density 0.190%

    No Known Activations